© 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. 5938
    Prev
    Next
    INDEX
    Explanations

    LaTeX-like code.

    oai_token-act-pair · gemini-2.0-flash

    \

    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
    SharedDtor
    -0.93
    uxxxx
    -0.83
    featureID
    -0.76
    GIVEREF
    -0.71
    LookAnd
    -0.69
    parsedMessage
    -0.68
    FieldBuilder
    -0.67
     resourceCulture
    -0.67
    енча
    -0.66
    -------------</
    -0.62
    POSITIVE LOGITS
     espir
    0.54
    ese
    0.48
    eq
    0.48
     Hanno
    0.47
     hvid
    0.47
     étrangers
    0.46
     hvit
    0.46
    Start
    0.43
    纲
    0.43
    hams
    0.42
    Activations Density 3.453%

    No Known Activations