© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14690
    Prev
    Next
    INDEX
    Explanations

    text excerpts that are enclosed in quotes or parentheses, and in some cases, extracts abbreviations or acronyms that may follow a phrase.

    oai_token-act-pair · gemini-2.0-flash

    quotation marks/punctuation

    np_max-act-logits · gemini-2.0-flash

    quotation marks

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    casian
    -0.25
    ,
    -0.24
    oray
    -0.24
    SPATH
    -0.23
    PMailer
    -0.23
    ổi
    -0.23
    logrus
    -0.21
    .
    -0.21
    byes
    -0.21
    StackNavigator
    -0.20
    POSITIVE LOGITS
    provisional
    0.73
    synthesis
    0.68
    satisfaction
    0.67
    acquisition
    0.67
    establishment
    0.66
    conspiracy
    0.66
    prevention
    0.66
    partnership
    0.66
    representative
    0.66
    adaptation
    0.66
    Activations Density 18.461%

    No Known Activations