© 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. 133001
    Prev
    Next
    INDEX
    Explanations

    Shadowrun and beach

    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
    وي
    1.02
    in
    1.01
    。
    0.99
    ды
    0.90
    できる
    0.88
    。\
    0.83
    1
    0.82
    大
    0.82
     الدين
    0.81
    ства
    0.79
    POSITIVE LOGITS
    า
    0.96
    ↵↵
    0.92
     bija
    0.91
     all
    0.90
    quakes
    0.88
     combating
    0.86
    u
    0.86
     ilmu
    0.84
     olnud
    0.83
     accounting
    0.82
    Activations Density 0.000%

    No Known Activations