© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127605
    Prev
    Next
    INDEX
    Explanations

    Honors and HYSA

    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_3_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
    ي
    0.82
    ले
    0.75
    ad
    0.74
    ت
    0.70
    ag
    0.67
    یی
    0.67
    ان
    0.66
    adai
    0.66
    ل
    0.66
    ﺍ
    0.66
    POSITIVE LOGITS
    ()")
    0.60
     ayudas
    0.58
     οποίο
    0.58
     установлен
    0.57
    ó
    0.57
    ى
    0.57
     plików
    0.56
    </th>
    0.55
    ii
    0.55
     atteint
    0.54
    Activations Density 0.000%

    No Known Activations