© 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. 45835
    Prev
    Next
    INDEX
    Explanations

    field, table, score, metrics, client, speed

    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
    ра
    0.86
    м
    0.86
    م
    0.84
    á
    0.78
     It
    0.75
    ja
    0.73
    ON
    0.73
    ti
    0.72
     is
    0.71
     to
    0.70
    POSITIVE LOGITS
    ويه
    0.66
    蟳
    0.61
    pción
    0.60
     تغيير
    0.60
    咟
    0.60
    이가
    0.59
     ιδ
    0.58
     براي
    0.57
    કિંગ
    0.56
    اديم
    0.55
    Activations Density 0.001%

    No Known Activations