© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197166
    Prev
    Next
    INDEX
    Explanations

    in place

    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_4_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
    .
    1.06
    ти
    1.05
    ana
    1.02
    є
    0.92
    h
    0.91
    ata
    0.88
    í
    0.88
    ৰ
    0.88
    ко
    0.85
    ara
    0.84
    POSITIVE LOGITS
    <0x80>
    1.05
    0
    0.95
     in
    0.93
    ٠
    0.83
    {},
    0.80
    {\
    0.77
    بيق
    0.77
    ０
    0.76
    عة
    0.75
    _{
    0.74
    Activations Density 0.002%

    No Known Activations