© 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-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261275
    Prev
    Next
    INDEX
    Explanations

    historic places and buildings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ۔
    1.69
     a
    1.45
    ។
    1.25
    ᱑
    1.23
    ።
    1.20
    는
    1.15
    我们
    1.13
     Бере
    1.13
    は
    1.13
    ।
    1.09
    POSITIVE LOGITS
    ies
    1.34
    م
    1.20
     or
    1.10
    ного
    1.03
    ί
    1.02
    ire
    1.00
    ä
    0.97
    ated
    0.95
    м
    0.95
    end
    0.95
    Activations Density 0.001%

    No Known Activations