© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108165
    Prev
    Next
    INDEX
    Explanations

    pref words

    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
    ী
    1.47
    ת
    1.45
    ය
    1.38
    ب
    1.33
    Τ
    1.27
    ח
    1.26
    트
    1.26
    تش
    1.25
    ों
    1.23
    లో
    1.22
    POSITIVE LOGITS
    1.29
    cknowled
    1.16
     is
    1.08
    是
    0.97
    с
    0.93
    <0xAC>
    0.93
     l
    0.91
    mi
    0.90
    <0x9B>
    0.89
    ores
    0.88
    Activations Density 0.003%

    No Known Activations