© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3379
    Prev
    Next
    INDEX
    Explanations

    sexually attractive people and clothing

    oai_token-act-pair · gemini-2.0-flash

    bodies and appearance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    LookAnd
    -0.54
    uxxxx
    -0.54
    look
    -0.50
     look
    -0.50
     bords
    -0.48
    Хьажоргаш
    -0.48
    Look
    -0.48
     bord
    -0.47
     marche
    -0.47
     Look
    -0.46
    POSITIVE LOGITS
    المراجع
    0.68
    ConfigureAwait
    0.68
    IMDG
    0.65
     onBind
    0.63
    bootstrapcdn
    0.59
     PhpStorm
    0.59
    amssymb
    0.57
    سمبر
    0.57
    nanoTime
    0.57
    twimg
    0.56
    Activations Density 0.401%

    No Known Activations