© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 36636
    Prev
    Next
    INDEX
    Explanations

    copyright and writer

    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_3_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
    <0x0D>
    1.05
    স
    0.67
    </b>
    0.66
    ay
    0.66
     integrate
    0.64
     a
    0.63
    ك
    0.63
    ará
    0.61
     و
    0.60
     س
    0.60
    POSITIVE LOGITS
     Allemagne
    0.72
    toare
    0.67
    nikiem
    0.66
    ной
    0.65
    صی
    0.65
    지
    0.64
    ですので
    0.64
     I
    0.63
    کش
    0.63
    کان
    0.62
    Activations Density 0.008%

    No Known Activations