© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131632
    Prev
    Next
    INDEX
    Explanations

    weekend

    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
    ي
    1.14
    р
    1.06
    ב
    1.03
    us
    1.02
     nymphs
    1.02
    ר
    0.98
     be
    0.98
     H
    0.97
    er
    0.96
     F
    0.95
    POSITIVE LOGITS
    dalam
    0.92
    ्स
    0.87
    ২
    0.86
    $
    0.86
    다
    0.85
    $)$.
    0.81
    awt
    0.80
    In
    0.78
    description
    0.77
    azaar
    0.77
    Activations Density 0.001%

    No Known Activations