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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31429
    Prev
    Next
    INDEX
    Explanations

    Levenshtein distance

    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
    le
    0.19
    a
    0.19
    an
    0.18
    h
    0.17
    o
    0.15
    in
    0.15
    f
    0.15
    are
    0.15
    ه
    0.14
    ne
    0.14
    POSITIVE LOGITS
    으로
    0.15
    스코
    0.14
    ভাবে
    0.14
    போக்கு
    0.14
    ת
    0.14
    由于
    0.14
     Acá
    0.14
    ensos
    0.14
     compartil
    0.13
    을
    0.13
    Activations Density 0.002%

    No Known Activations