© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3195
    Prev
    Next
    INDEX
    Explanations

    source code or configuration file snippets

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     onOptions
    -0.88
     HasFactory
    -0.87
    aarrggbb
    -0.84
     viewDidLoad
    -0.84
    DeleteBehavior
    -0.82
    fromnode
    -0.81
    __(/*!
    -0.78
    NewLabel
    -0.78
     متعلقه
    -0.77
     ويكيپ
    -0.76
    POSITIVE LOGITS
    <bos>
    2.33
    '
    0.68
    ’
    0.65
    ,
    0.61
     the
    0.56
    a
    0.55
    ↵↵
    0.55
     and
    0.55
    ↵
    0.54
    ing
    0.51
    Activations Density 1.191%

    No Known Activations