© 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. 3825
    Prev
    Next
    INDEX
    Explanations

    words related to body parts, especially the mouth, and also some words that co-occur with those body parts

    oai_token-act-pair · gemini-2.0-flash

    mouth

    np_max-act · gemini-2.0-flash
    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
     mouth
    -1.28
    mouth
    -1.16
     mouths
    -1.14
    Mouth
    -1.02
     Mouth
    -0.97
    mouthed
    -0.94
    MOUTH
    -0.90
     mulut
    -0.74
     bouche
    -0.72
     mout
    -0.71
    POSITIVE LOGITS
    lá
    0.54
    τευ
    0.53
     ***!
    0.53
     skak
    0.51
    Примечания
    0.49
    lapsingToolbar
    0.49
    mería
    0.48
    MemoryWarning
    0.45
    ksikon
    0.45
     متحده
    0.45
    Activations Density 11.527%

    No Known Activations