© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106388
    Prev
    Next
    INDEX
    Explanations

    divide-and-conquer algorithm

    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_1_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
     a
    1.70
     to
    1.34
    to
    1.29
    de
    1.16
     be
    1.11
    ler
    1.08
    ut
    1.02
     at
    1.00
    ana
    1.00
    -
    1.00
    POSITIVE LOGITS
    ك
    1.31
    ка
    1.28
    و
    1.25
    Parrocchia
    0.93
     второй
    0.89
    는
    0.86
     भागों
    0.85
    ج
    0.85
     ചേർ
    0.84
    یر
    0.84
    Activations Density 0.002%

    No Known Activations