© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 632
    Prev
    Next
    INDEX
    Explanations

    descriptions of skin or its color

    oai_token-act-pair · gemini-2.0-flash

    skin

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     autorytatywna
    -0.65
    Autoritní
    -0.63
    Referencer
    -0.59
    Datuak
    -0.56
    Atsauces
    -0.50
    CreateMap
    -0.48
    Rptr
    -0.47
     JpaRepository
    -0.46
    Šaltiniai
    -0.46
    ībā
    -0.46
    POSITIVE LOGITS
     skin
    1.31
     skins
    1.01
     skinned
    0.98
     Skin
    0.97
    skin
    0.96
     SKIN
    0.96
    Skin
    0.91
     Skins
    0.83
     peau
    0.82
    skins
    0.79
    Activations Density 0.743%

    No Known Activations