© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 540
    Prev
    Next
    INDEX
    Explanations

    text within parentheses, particularly those associated with citations or technical/legal language

    oai_token-act-pair · gemini-2.0-flash

    structured text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    LEncoder
    -0.62
    MessageOf
    -0.57
    iconque
    -0.55
    wps
    -0.54
    ỡng
    -0.53
    stě
    -0.53
    multirow
    -0.52
    aarrggbb
    -0.52
     deliberate
    -0.51
    PreExecute
    -0.51
    POSITIVE LOGITS
    GraphicsUnit
    0.68
    MemoryWarning
    0.67
    astéroïdes
    0.65
     gainera
    0.60
    CodeAttribute
    0.59
     EnglishChoose
    0.59
    nodoc
    0.57
     amphi
    0.57
     StatelessWidget
    0.57
     Sixt
    0.57
    Activations Density 0.759%

    No Known Activations