© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203307
    Prev
    Next
    INDEX
    Explanations

    execute, request, sort

    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_12_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
    ぁ
    0.35
    ؟
    0.32
    а
    0.32
    Alaska
    0.32
    د
    0.30
    Maui
    0.29
    ?
    0.29
    ”
    0.29
    "
    0.29
     ؟
    0.29
    POSITIVE LOGITS
     creditor
    0.32
     engender
    0.29
    扈
    0.29
    ക്കാര
    0.28
    uje
    0.27
     racial
    0.27
     chronograph
    0.27
    zenie
    0.26
    চ্ছেদ
    0.26
     ক্ষেত্র
    0.26
    Activations Density 0.000%

    No Known Activations