© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28167
    Prev
    Next
    INDEX
    Explanations

    "VK_KHR_" and "::after"

    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_40_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
     identification
    0.47
    Identification
    0.46
     ဝ
    0.46
     Identification
    0.44
    getAsDouble
    0.41
    蜢
    0.41
     identificación
    0.40
     fournis
    0.40
     shrinking
    0.39
     condensing
    0.38
    POSITIVE LOGITS
    foundation
    0.41
    theme
    0.39
    cii
    0.39
     foundations
    0.39
     سلمان
    0.39
    獣
    0.38
    Jupiter
    0.37
    Platz
    0.37
    ieht
    0.35
     tvr
    0.35
    Activations Density 0.000%

    No Known Activations