© 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. 132497
    Prev
    Next
    INDEX
    Explanations

    Buchenwald, Xianlin, Dunlin

    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
    nya
    1.12
     on
    1.11
    の
    1.02
     is
    0.99
    AH
    0.97
    的
    0.96
    AZIONE
    0.93
    ıyla
    0.92
    が
    0.92
    AM
    0.91
    POSITIVE LOGITS
    z
    1.60
    f
    1.43
    ين
    1.23
    ాలు
    1.23
    ى
    1.15
    g
    1.14
    ون
    1.13
    ians
    1.05
    inth
    1.05
    ش
    1.05
    Activations Density 0.000%

    No Known Activations