© 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. 13926
    Prev
    Next
    INDEX
    Explanations

    java code

    oai_token-act-pair · gemini-2.0-flash

    google

    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
    bibfield
    -1.12
    BibitemShut
    -1.06
    bibinfo
    -1.03
     فريبيس
    -0.99
     myſelf
    -0.97
    æus
    -0.86
    ^(@)
    -0.85
     ſeveral
    -0.85
    XmlAccessType
    -0.83
    citenamefont
    -0.83
    POSITIVE LOGITS
    (
    0.64
    श
    0.58
    S
    0.58
    use
    0.57
    Sk
    0.57
    .
    0.56
    الإنجليزية
    0.56
    শ
    0.56
    K
    0.56
    tak
    0.56
    Activations Density 0.199%

    No Known Activations