© 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. 5625
    Prev
    Next
    INDEX
    Explanations

    words referring to regions and councils

    oai_token-act-pair · gemini-2.0-flash

    Local councils and law

    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
     council
    -2.78
    Council
    -2.58
     Council
    -2.56
    council
    -2.55
     councils
    -2.50
     COUNCIL
    -2.47
     Councils
    -2.36
    UNCIL
    -1.83
     Coun
    -1.82
    Coun
    -1.78
    POSITIVE LOGITS
     defaultstate
    0.54
     décédé
    0.49
    XmlAccessorType
    0.49
    లాలు
    0.46
    mette
    0.46
     Gato
    0.46
    ligator
    0.43
     persi
    0.42
     Patagonia
    0.42
     décontract
    0.42
    Activations Density 1.553%

    No Known Activations