© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12390
    Prev
    Next
    INDEX
    Explanations

    food recipes

    oai_token-act-pair · gemini-2.0-flash

    recipes and procedures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ArrowToggle
    -0.84
    ьаж
    -0.72
    tonsoft
    -0.72
    FieldBuilder
    -0.71
     estekak
    -0.71
     unknownFields
    -0.69
    '])->
    -0.69
     Roskov
    -0.69
    extAlignment
    -0.68
     nahilalakip
    -0.66
    POSITIVE LOGITS
    ppar
    0.41
     medium
    0.41
    Портал
    0.39
     middel
    0.39
     covered
    0.39
    ar
    0.39
     Thirteen
    0.38
     fó
    0.38
     mercad
    0.37
    ponses
    0.37
    Activations Density 1.581%

    No Known Activations