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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11538
    Prev
    Next
    INDEX
    Explanations

    code snippets that are part of software packages being installed or containing math operations

    oai_token-act-pair · gemini-2.0-flash

    words with special characters or old English letters

    np_token-act-pair-logits · gpt-4o-mini

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    </b>
    -0.66
    GraphicsUnit
    -0.65
    </i>
    -0.64
     Lo
    -0.60
     Op
    -0.57
    DockStyle
    -0.57
    ⓧ
    -0.57
    Lo
    -0.57
    SequentialGroup
    -0.57
     Cas
    -0.56
    POSITIVE LOGITS
     uſed
    0.82
     Theſe
    0.82
     Efq
    0.80
     Monfieur
    0.79
     anſ
    0.74
     uſe
    0.71
     caufe
    0.71
     étoient
    0.69
     poffe
    0.68
     poffible
    0.68
    Activations Density 8.189%

    No Known Activations