© 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. 14938
    Prev
    Next
    INDEX
    Explanations

    locations, money amounts, dates, court cases, and numbers

    oai_token-act-pair · gemini-2.0-flash

    state abbreviations

    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
    oa̍t
    -0.71
    __()
    -0.70
    thâu
    -0.67
    +#+
    -0.65
     referenties
    -0.61
    autoconfigure
    -0.59
    зулта
    -0.57
     Baillargeon
    -0.57
    ibatis
    -0.55
    elemField
    -0.54
    POSITIVE LOGITS
     Mass
    1.00
     Wis
    0.91
     Mich
    0.91
    Mass
    0.88
     Fla
    0.88
     Ont
    0.84
     Va
    0.82
     Ala
    0.79
     Pa
    0.78
    Wis
    0.78
    Activations Density 8.631%

    No Known Activations