© 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. 267
    Prev
    Next
    INDEX
    Explanations

    proper names for people and places, especially Italian ones, often in a historical context.

    oai_token-act-pair · gemini-2.0-flash

    Italian

    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
     Khu
    -0.54
     defaultstate
    -0.54
     Koy
    -0.49
     Uy
    -0.49
     maer
    -0.48
     scattata
    -0.48
    Khu
    -0.48
     Hoon
    -0.47
     nemico
    -0.46
     titolata
    -0.46
    POSITIVE LOGITS
     Italian
    0.75
     Italy
    0.69
    Italian
    0.66
     Italians
    0.62
    Italy
    0.60
     Giuseppe
    0.60
     ITAL
    0.59
    Luigi
    0.59
     Luigi
    0.58
    izzi
    0.58
    Activations Density 17.801%

    No Known Activations