© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28907
    Prev
    Next
    INDEX
    Explanations

    code blocks and Python syntax

    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_10_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
    the
    0.57
    Е
    0.56
     जिसमें
    0.55
    ।
    0.52
     dependents
    0.50
     کس
    0.49
    3
    0.46
     Два
    0.45
     Canadi
    0.45
    splitLength
    0.45
    POSITIVE LOGITS
    ى
    0.61
    的力量
    0.44
    h
    0.41
    ρα
    0.38
    <0xAC>
    0.38
    <0x99>
    0.38
    lə
    0.37
    та
    0.37
    lük
    0.36
    <0x0D>
    0.36
    Activations Density 0.047%

    No Known Activations