© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228426
    Prev
    Next
    INDEX
    Explanations

    all-rounder

    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_6_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
    s
    1.35
    t
    1.09
    的
    1.08
    the
    1.05
    m
    1.04
    w
    1.02
    の
    0.98
    d
    0.96
    ים
    0.95
    in
    0.93
    POSITIVE LOGITS
     свобод
    0.93
     необходи
    0.92
    ↵↵
    0.90
     equivoc
    0.84
     ৫
    0.82
     escaping
    0.82
     δύο
    0.82
     நீங்கள்
    0.82
     inconclusive
    0.82
     bolstering
    0.82
    Activations Density 0.003%

    No Known Activations