© 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. 241782
    Prev
    Next
    INDEX
    Explanations

    local assignment, var definition

    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
     abstrak
    0.42
    頨
    0.39
    abstract
    0.39
     গৌর
    0.38
     sovr
    0.38
     سته
    0.38
    ಭವ
    0.38
     SP
    0.37
    ่อง
    0.37
     abstr
    0.37
    POSITIVE LOGITS
    रूम
    0.39
     quad
    0.35
    нии
    0.35
    嗌
    0.34
    िकी
    0.34
    বিরোধী
    0.34
     существу
    0.33
    veli
    0.33
     ٹی
    0.33
    தர்
    0.33
    Activations Density 0.000%

    No Known Activations