© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210964
    Prev
    Next
    INDEX
    Explanations

    phone

    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_5_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
    ка
    1.36
    ли
    1.29
     or
    1.20
    ری
    1.15
    ेंट
    1.13
    اری
    1.12
    де
    1.09
    ą
    1.09
    ↵
    1.02
    シング
    1.01
    POSITIVE LOGITS
    ي
    1.20
     في
    1.05
    اك
    1.02
    و
    1.01
    在
    1.00
    ol
    0.95
    ។
    0.93
    ians
    0.90
    $.}
    0.89
    0.89
    Activations Density 0.002%

    No Known Activations