© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12817
    Prev
    Next
    INDEX
    Explanations

    HTML or code snippets with table and method information

    oai_token-act-pair · gemini-2.0-flash

    HTML code

    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
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -1.98
    ^(@)
    -1.95
     مشين
    -1.89
     EconPapers
    -1.80
    NUMX
    -1.80
    IntoConstraints
    -1.78
    parsedMessage
    -1.76
    BibitemShut
    -1.73
    "):
    -1.73
    $.
    -1.70
    POSITIVE LOGITS
    <bos>
    1.51
    '
    1.24
    1
    1.20
    2
    1.17
    3
    1.09
    ,
    1.07
    a
    1.02
    c
    1.02
    ↵↵
    1.01
    to
    1.01
    Activations Density 1.006%

    No Known Activations