© 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. 8079
    Prev
    Next
    INDEX
    Explanations

    words related to business and finances

    oai_token-act-pair · gemini-2.0-flash

    Quantities

    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
    MigrationBuilder
    -0.91
    BeginInit
    -0.91
     Main
    -0.75
     Most
    -0.74
     Great
    -0.74
     Proven
    -0.72
    EndProject
    -0.71
     Bad
    -0.70
    Main
    -0.69
     Good
    -0.68
    POSITIVE LOGITS
     Terms
    0.64
     Float
    0.59
    Singles
    0.56
     Three
    0.56
     Five
    0.54
     Tandem
    0.53
    Twelve
    0.52
     Bilateral
    0.50
     Double
    0.50
    Float
    0.50
    Activations Density 7.952%

    No Known Activations