© 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. 14897
    Prev
    Next
    INDEX
    Explanations

    colons, parenthetical phrases, and sometimes the names of places/institutions

    oai_token-act-pair · 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
     colorful
    -0.66
     illustration
    -0.63
     colourful
    -0.62
     artwork
    -0.60
     graphic
    -0.59
     illustrations
    -0.59
     artistic
    -0.59
     sculptured
    -0.57
     inspired
    -0.57
     aesthetic
    -0.56
    POSITIVE LOGITS
     warrant
    0.67
     warranty
    0.65
     fee
    0.64
     subsidy
    0.63
     demand
    0.62
     contract
    0.60
     guarantee
    0.60
     warrants
    0.56
     budget
    0.54
     rebate
    0.54
    Activations Density 9.207%

    No Known Activations