© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3078
    Prev
    Next
    INDEX
    Explanations

    technical or legal terms, especially those related to programming and variable names

    oai_token-act-pair · gemini-2.0-flash

    sign

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeFieldEnd
    -0.65
    ουργ
    -0.64
     carriera
    -0.60
    AnchorStyles
    -0.59
    VersionUID
    -0.58
    Geplaatst
    -0.57
    anteed
    -0.54
     Alab
    -0.54
    存于互联网档案馆
    -0.54
    Spoljašnje
    -0.54
    POSITIVE LOGITS
     sign
    1.04
     Sign
    0.82
     signs
    0.80
    Sign
    0.79
    sign
    0.76
     symbol
    0.76
     SIGN
    0.73
    サイン
    0.73
     signo
    0.70
     signal
    0.69
    Activations Density 4.355%

    No Known Activations