© 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. 202934
    Prev
    Next
    INDEX
    Explanations

    Amazon Prime Video

    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
     Красно
    0.98
    0.98
     delanter
    0.93
     стомато
    0.93
    l
    0.91
     Кали
    0.86
     backgroundImg
    0.86
     Giacomo
    0.84
    お客
    0.84
    आज
    0.83
    POSITIVE LOGITS
    ם
    1.09
    ется
    1.08
     in
    1.05
    et
    1.00
    U
    0.97
    ↵
    0.96
     be
    0.96
    Y
    0.95
    S
    0.94
     an
    0.93
    Activations Density 0.000%

    No Known Activations