© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6022
    Prev
    Next
    INDEX
    Explanations

    words related to software reviews and creativity

    oai_token-act-pair · gemini-2.0-flash

    creative endeavors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     creative
    -2.28
    Creative
    -2.16
     Creative
    -2.13
    creative
    -2.02
     creativity
    -1.78
     creatively
    -1.77
    Creativity
    -1.73
     creativa
    -1.71
     Creativity
    -1.66
     kreativ
    -1.62
    POSITIVE LOGITS
    ViewImports
    0.91
    mybatisplus
    0.76
    DebuggerNonUser
    0.70
    MigrationBuilder
    0.70
    ⓧ
    0.69
    ANTLR
    0.68
    WebServlet
    0.67
    IVersion
    0.65
     iprot
    0.64
    elemField
    0.63
    Activations Density 2.081%

    No Known Activations