© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14466
    Prev
    Next
    INDEX
    Explanations

    descriptions of hair

    oai_token-act-pair · gemini-2.0-flash

    hair/medical related

    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
    Negative Logits
     numberWith
    -0.56
    __':
    -0.56
    Adopted
    -0.54
     sposa
    -0.52
    Beijos
    -0.52
    __":
    -0.52
    gazette
    -0.51
     intérieure
    -0.50
    AWARDS
    -0.49
    RegistryLite
    -0.49
    POSITIVE LOGITS
    ArgsConstructor
    0.62
    DebuggerNonUser
    0.60
     Paglinawan
    0.54
    saraba
    0.53
    TextUtils
    0.49
     StatelessWidget
    0.48
     Beal
    0.48
    GroupLayout
    0.48
     crossorigin
    0.48
     newBuilder
    0.47
    Activations Density 1.758%

    No Known Activations