© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9323
    Prev
    Next
    INDEX
    Explanations

    code with annotations

    oai_token-act-pair · gemini-2.0-flash

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     coû
    -0.53
     Jurí
    -0.53
     tôt
    -0.52
     quelcon
    -0.51
     judiciaire
    -0.51
     démocr
    -0.48
     quelconque
    -0.47
    ennemi
    -0.47
     écout
    -0.46
     élu
    -0.46
    POSITIVE LOGITS
    RenderAtEndOf
    0.73
    DoubleQuotes
    0.67
    AddTagHelper
    0.65
    rungsseite
    0.60
    ArgsConstructor
    0.60
    MLLoader
    0.60
    }`}>
    0.59
    IsContent
    0.58
    "]);
    0.58
    GOTREF
    0.57
    Activations Density 3.669%

    No Known Activations