© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3183
    Prev
    Next
    INDEX
    Explanations

    code related to Swift protocol buffer decoding

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    XmlAccessType
    -0.66
     وتسجيلات
    -0.64
     Theſe
    -0.59
     صوتيه
    -0.57
     myſelf
    -0.56
     ſeveral
    -0.50
     parma
    -0.50
     impedance
    -0.50
    ſelf
    -0.50
    Legături
    -0.50
    POSITIVE LOGITS
    windowFixed
    0.72
    ChildScrollView
    0.53
     sä
    0.53
     Cataloging
    0.52
    벗
    0.51
    Typography
    0.50
    oredCriteria
    0.48
    restling
    0.47
     useState
    0.47
    qtype
    0.47
    Activations Density 1.502%

    No Known Activations