© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2287
    Prev
    Next
    INDEX
    Explanations

    words that are overall positive or indicate performing a task

    oai_token-act-pair · gemini-2.0-flash

    tokens related to self-reference or introspection

    np_token-act-pair-logits · gpt-4o-mini
    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
    .
    -0.91
    ,
    -0.82
    ?
    -0.70
     and
    -0.65
    !
    -0.63
     (
    -0.61
     -
    -0.58
    ।
    -0.57
    ;
    -0.54
     I
    -0.54
    POSITIVE LOGITS
    ImageContext
    1.16
     itſelf
    1.08
     iſt
    1.06
     myſelf
    1.03
     againſt
    1.02
    __':
    1.01
    RenderAtEndOf
    0.96
    ſelves
    0.94
    клопе
    0.93
     صوتيه
    0.93
    Activations Density 8.928%

    No Known Activations