© 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. 5513
    Prev
    Next
    INDEX
    Explanations

    the words which make up technical descriptions.

    oai_token-act-pair · gemini-2.0-flash

    say body parts, lower half

    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
     Wind
    -0.50
    Dare
    -0.48
     wind
    -0.47
    Wind
    -0.47
     Smith
    -0.47
     western
    -0.47
     southwest
    -0.46
    aguer
    -0.45
    äß
    -0.45
     southern
    -0.44
    POSITIVE LOGITS
     consultato
    0.86
    expandindo
    0.84
    MigrationBuilder
    0.75
    enumii
    0.72
    IsContent
    0.68
    IsMutable
    0.67
    CppMethod
    0.66
    CodeAttribute
    0.65
    WriteLiteral
    0.63
    +#+
    0.63
    Activations Density 1.594%

    No Known Activations