© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3563
    Prev
    Next
    INDEX
    Explanations

    mathematical equations or expressions

    oai_token-act-pair · gemini-2.0-flash

    Math equations

    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
    ^
    -0.81
    +
    -0.75
    +}\
    -0.62
    \
    -0.58
    *
    -0.57
     disponibilités
    -0.47
    -
    -0.45
    (
    -0.42
    ^=
    -0.42
    ształ
    -0.42
    POSITIVE LOGITS
     مرئيه
    0.67
    Tikang
    0.66
    Jeografia
    0.62
    Искәрмәләр
    0.59
     समीक्षक
    0.59
     jspb
    0.58
    InSection
    0.57
    pexpr
    0.57
    selves
    0.57
    )|^{
    0.57
    Activations Density 6.327%

    No Known Activations