© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82864
    Prev
    Next
    INDEX
    Explanations

    valuation

    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_0_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
    م
    2.55
    با
    1.84
    न
    1.80
    나
    1.75
    به
    1.66
    ق
    1.64
    ین
    1.63
    ب
    1.55
    은
    1.55
    مع
    1.53
    POSITIVE LOGITS
    ే
    1.41
    ૦
    1.40
     moze
    1.39
    er
    1.38
    ០
    1.35
    0
    1.30
    ﺕ
    1.30
     приня
    1.27
     magie
    1.27
     сдела
    1.27
    Activations Density 0.001%

    No Known Activations