© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197322
    Prev
    Next
    INDEX
    Explanations

    safety precautions

    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_4_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
    ف
    1.17
    ية
    1.11
    ר
    1.11
    ור
    1.08
    ર
    1.04
    {
    1.02
    س
    1.00
    м
    0.99
    ра
    0.99
    ле
    0.97
    POSITIVE LOGITS
    asta
    0.82
     on
    0.82
    ically
    0.82
    ning
    0.80
     of
    0.79
    ни
    0.77
    nd
    0.76
    ước
    0.75
    uate
    0.74
    ading
    0.74
    Activations Density 0.000%

    No Known Activations