© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13557
    Prev
    Next
    INDEX
    Explanations

    instances of people being moved or injured.

    oai_token-act-pair · gemini-2.0-flash

    events happening to someone

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     back
    -0.83
     Back
    -0.69
    Back
    -0.66
     BACK
    -0.60
    back
    -0.58
     tilbake
    -0.52
    BACK
    -0.51
     zurück
    -0.46
    バック
    -0.46
     espalda
    -0.46
    POSITIVE LOGITS
     myſelf
    1.00
     itſelf
    0.99
    ſelf
    0.94
     whoſe
    0.93
     purpoſe
    0.91
     raiſ
    0.89
     pleaſure
    0.89
     himſelf
    0.88
     Houſe
    0.85
     ſeveral
    0.82
    Activations Density 13.508%

    No Known Activations