© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2869
    Prev
    Next
    INDEX
    Explanations

    the [adjective/noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    러
    0.73
     कहा
    0.72
    smanship
    0.70
    ^{[\
    0.70
     pertumbuhan
    0.70
    ATION
    0.70
    ວນ
    0.69
     peluang
    0.69
    們
    0.69
    م
    0.69
    POSITIVE LOGITS
    as
    0.83
    Least
    0.75
     heir
    0.70
    о
    0.68
     Etern
    0.64
     least
    0.64
    ‍
    0.63
    a
    0.63
    z
    0.61
     edhe
    0.61
    Activations Density 0.096%

    No Known Activations