© 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. 11891
    Prev
    Next
    INDEX
    Explanations

    tokens related to business activities like gardening, websites and branding

    oai_token-act-pair · gemini-2.0-flash

    punctuation mark "."

    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
    hitheater
    -0.72
    httphttps
    -0.69
    FAVOR
    -0.69
     coloring
    -0.69
     molds
    -0.68
     Coloring
    -0.66
     colored
    -0.65
     favorites
    -0.65
     colorless
    -0.65
     favorite
    -0.64
    POSITIVE LOGITS
    MigrationBuilder
    0.73
    Datuak
    0.66
     Wikimedijinoj
    0.56
    AddTagHelper
    0.49
    eneral
    0.47
    lais
    0.47
    '
    0.45
     nahilalakip
    0.44
    esson
    0.43
     ProtoMessage
    0.43
    Activations Density 12.487%

    No Known Activations