© 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. 8430
    Prev
    Next
    INDEX
    Explanations

    words used in informal, conversational language, like posts, comments, and reviews

    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
     økonom
    -0.55
    kembang
    -0.49
     szív
    -0.49
    __':
    -0.48
     kereszt
    -0.47
     bolig
    -0.47
     dår
    -0.47
     keskus
    -0.46
     læng
    -0.46
    __":
    -0.46
    POSITIVE LOGITS
     myſelf
    1.05
     themſelves
    1.00
     himſelf
    0.95
     Monfieur
    0.94
     Majefty
    0.83
     ſeveral
    0.83
     Jefus
    0.82
     itſelf
    0.82
     ſtand
    0.80
     whoſe
    0.80
    Activations Density 36.065%

    No Known Activations