© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261074
    Prev
    Next
    INDEX
    Explanations

    Connect Four, 4 wins, TV

    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_5_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
    ني
    1.27
    ور
    1.16
    O
    1.13
    ICK
    1.09
    AST
    1.09
    iden
    1.08
    اد
    1.06
    UL
    1.05
    EC
    1.05
    مر
    1.04
    POSITIVE LOGITS
    ت
    1.05
    ası
    0.97
    и
    0.96
    ledes
    0.95
    uje
    0.94
     grizz
    0.93
    i
    0.93
     berubah
    0.92
     второй
    0.91
    る
    0.91
    Activations Density 0.000%

    No Known Activations