© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39499
    Prev
    Next
    INDEX
    Explanations

    quotation mark followed by words

    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_11_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
     orij
    0.51
    urkan
    0.49
    стина
    0.48
    biggr
    0.47
    ментів
    0.47
    ጒ
    0.46
    Pixel
    0.46
     نست
    0.46
     автофо
    0.45
    バリー
    0.45
    POSITIVE LOGITS
    ę
    0.59
    ól
    0.57
     for
    0.55
     life
    0.54
    ál
    0.54
    ;
    0.54
     '
    0.54
    á
    0.54
    ge
    0.53
    ys
    0.52
    Activations Density 0.034%

    No Known Activations