© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10104
    Prev
    Next
    INDEX
    Explanations

    code documentation and parameter/return statements, plus the word "state"

    oai_token-act-pair · gemini-2.0-flash

    PHP code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    GEBURTS
    -0.69
    oa̍t
    -0.68
    曖昧さ回避
    -0.63
    期刊论文
    -0.57
    NameInMap
    -0.56
    πως
    -0.56
    enterOuterAlt
    -0.55
    tonode
    -0.55
    __*/
    -0.54
    Kariera
    -0.53
    POSITIVE LOGITS
    StoryboardSegue
    0.72
    gdx
    0.66
     صوتيه
    0.55
     RoutedEventArgs
    0.54
    multirow
    0.53
    AnchorTagHelper
    0.53
    XtraGrid
    0.51
    mybatisplus
    0.51
    osexuality
    0.50
     mixed
    0.49
    Activations Density 0.240%

    No Known Activations