© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11693
    Prev
    Next
    INDEX
    Explanations

    abbreviations of sports teams, certain HTML tags and journal article references.

    oai_token-act-pair · gemini-2.0-flash

    Code, paths, and technical

    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
    awtextra
    -0.54
    SOUNDBITE
    -0.54
    rayage
    -0.52
    ள
    -0.52
     T
    -0.50
     ?
    -0.49
    züge
    -0.49
     snippetHide
    -0.49
    ള
    -0.48
    rrggbb
    -0.47
    POSITIVE LOGITS
     Efq
    0.71
     Theſe
    0.70
     Diſ
    0.68
     Hej
    0.68
     Reſ
    0.67
     Monfieur
    0.66
     Chriftian
    0.65
     ſeveral
    0.65
     Jefus
    0.64
     Conſ
    0.64
    Activations Density 0.163%

    No Known Activations