© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16325
    Prev
    Next
    INDEX
    Explanations

    years, locations and people's occupations

    oai_token-act-pair · gemini-2.0-flash

    Scandanavian context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     kasarigan
    -0.68
     Norwegian
    -0.66
     Norway
    -0.66
     Norwe
    -0.65
     Sweden
    -0.65
     danish
    -0.64
    Norway
    -0.63
    الإنجليزية
    -0.63
     Scandinavian
    -0.63
     Danish
    -0.62
    POSITIVE LOGITS
     ái
    0.52
    futbolista
    0.52
    kes
    0.49
    kos
    0.48
     fronteras
    0.48
     rând
    0.48
     ferrocarril
    0.48
    AsUp
    0.47
    WEBPACK
    0.47
     animación
    0.47
    Activations Density 4.207%

    No Known Activations