© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13427
    Prev
    Next
    INDEX
    Explanations

    words describing the parts or processes of creating musical instruments or stone tools

    oai_token-act-pair · gemini-2.0-flash

    terms related to crafting

    np_token-act-pair-logits · gpt-4o-mini

    craft

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     AssemblyCulture
    -0.71
     незавершена
    -0.71
    MemoryWarning
    -0.68
    TagMode
    -0.68
     noqa
    -0.67
    saraba
    -0.65
    principalTable
    -0.63
     ExecuteAsync
    -0.61
    Portail
    -0.60
     ©️
    -0.60
    POSITIVE LOGITS
     craft
    1.20
     crafts
    1.12
     Craft
    1.03
     Crafts
    0.95
    crafts
    0.95
     crafting
    0.91
    craft
    0.91
     carving
    0.90
     craftsman
    0.89
     craftsmen
    0.87
    Activations Density 1.556%

    No Known Activations