© 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-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32688
    Prev
    Next
    INDEX
    Explanations

    previously, but now

    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_7_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
    ↵
    0.92
    é
    0.69
    id
    0.65
    f
    0.64
     మొదటి
    0.64
    ad
    0.63
    ð
    0.61
    í
    0.61
    ğ
    0.61
     čega
    0.60
    POSITIVE LOGITS
    0.73
     venons
    0.73
    ول
    0.71
     that
    0.70
     التي
    0.70
    리가
    0.68
     الم
    0.66
    ности
    0.64
    ON
    0.63
     anions
    0.62
    Activations Density 0.001%

    No Known Activations