© 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. 39803
    Prev
    Next
    INDEX
    Explanations

    confirmation "yes"

    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
    ed
    0.79
    '
    0.65
    d
    0.57
     swagger
    0.56
    ur
    0.55
    an
    0.54
    eder
    0.53
    വിന്റെ
    0.52
    dari
    0.52
    g
    0.52
    POSITIVE LOGITS
     экрана
    0.66
     innym
    0.62
    अधिकांश
    0.61
    C
    0.60
    㦣
    0.60
    %。
    0.59
     밝혔
    0.59
    Ин
    0.57
    地说
    0.57
     algunos
    0.56
    Activations Density 0.004%

    No Known Activations