© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 110447
    Prev
    Next
    INDEX
    Explanations

    triton or tranches

    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
     for
    1.12
    ur
    1.11
    s
    1.04
    t
    1.01
    ش
    0.97
     of
    0.96
    ty
    0.95
    0
    0.93
    ط
    0.93
    IP
    0.89
    POSITIVE LOGITS
    ۴
    0.97
    ↵
    0.86
    の話
    0.84
    は
    0.84
    ции
    0.82
    な
    0.80
    ے
    0.80
    ۵
    0.78
    ление
    0.77
    iamo
    0.77
    Activations Density 0.001%

    No Known Activations