© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10289
    Prev
    Next
    INDEX
    Explanations

    research-related words, especially those related to chemistry, biology, and experimentation, and measurements.

    oai_token-act-pair · gemini-2.0-flash

    scientific experimental processes

    np_max-act · gemini-2.0-flash

    past participle verbs

    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_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Efq
    -0.97
     myſelf
    -0.92
    fjspx
    -0.92
     Jefus
    -0.90
    TagMode
    -0.90
     houſe
    -0.88
    parsedMessage
    -0.86
     itſelf
    -0.86
     Houſe
    -0.84
    ſelf
    -0.84
    POSITIVE LOGITS
    <bos>
    1.08
     I
    0.49
     the
    0.49
     i
    0.48
    全
    0.45
     
    0.44
    .
    0.44
    !
    0.44
     -
    0.42
    -
    0.41
    Activations Density 7.330%

    No Known Activations