© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8270
    Prev
    Next
    INDEX
    Explanations

    language related to fundraising, donations, and support.

    oai_token-act-pair · gemini-2.0-flash

    donate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     дописавши
    -0.80
    KEYCODE
    -0.77
    kháu
    -0.76
    ztály
    -0.70
    MLLoader
    -0.70
     Efq
    -0.68
    RegressionTest
    -0.66
    GraphicsUnit
    -0.66
     հղումներ
    -0.66
     Roskov
    -0.64
    POSITIVE LOGITS
    DoubleQuotes
    0.43
    ArgsConstructor
    0.42
    Viitteet
    0.36
     V
    0.36
     presents
    0.35
     zusammenge
    0.35
     cadeau
    0.34
    :^(
    0.34
    ABLE
    0.34
     pasillo
    0.34
    Activations Density 0.168%

    No Known Activations