© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13358
    Prev
    Next
    INDEX
    Explanations

    years, citations, and other references to legal language

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     devrez
    -0.62
    izoen
    -0.54
     تضيفلها
    -0.48
    impianto
    -0.47
    Idioma
    -0.47
    сылкі
    -0.47
    ￡
    -0.46
     igång
    -0.46
     noDo
    -0.46
    iibo
    -0.46
    POSITIVE LOGITS
    ########.
    0.60
    CodeAttribute
    0.60
    WriteLiteral
    0.60
    RegressionTest
    0.59
    protoimpl
    0.52
    ArgsConstructor
    0.52
    :+:
    0.50
    roupa
    0.50
    MVH
    0.50
     AspNetCore
    0.50
    Activations Density 3.240%

    No Known Activations