© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134472
    Prev
    Next
    INDEX
    Explanations

    meister skill titles

    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_6_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
    to
    0.90
    ado
    0.88
    ton
    0.84
    -
    0.83
    는
    0.72
    ails
    0.71
    ón
    0.71
    uring
    0.71
    hale
    0.71
    that
    0.70
    POSITIVE LOGITS
     for
    0.89
     amerikanischen
    0.78
    すぐに
    0.73
     privaten
    0.71
    <unused2140>
    0.69
     اكبر
    0.68
     canadien
    0.68
     adev
    0.68
     مؤرشف
    0.67
    ྕ
    0.67
    Activations Density 0.000%

    No Known Activations