© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111327
    Prev
    Next
    INDEX
    Explanations

    Hadoop

    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_2_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
     on
    2.09
    ס
    1.73
     by
    1.57
     with
    1.55
     that
    1.52
     to
    1.41
    ट
    1.41
    م
    1.39
    리
    1.30
    ب
    1.27
    POSITIVE LOGITS
    in
    1.17
    வ்வேறு
    0.91
    fhir
    0.90
    戞
    0.89
    嶈
    0.87
    嶆
    0.86
    و
    0.85
    ள்ளனர்
    0.81
    inę
    0.80
    ков
    0.80
    Activations Density 0.000%

    No Known Activations