© 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. 12592
    Prev
    Next
    INDEX
    Explanations

    dyn std::error

    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
     jab
    0.40
    ">=</
    0.39
     spirito
    0.39
    cline
    0.38
    atom
    0.38
    ång
    0.37
     imperfection
    0.37
    近づ
    0.37
    ेटिक
    0.37
     cory
    0.36
    POSITIVE LOGITS
     প্রশাস
    0.38
    🇪
    0.38
    ⅛
    0.37
     Heine
    0.36
    佣
    0.35
     Payable
    0.35
     diar
    0.35
    payable
    0.34
     मलेशिया
    0.34
     Franco
    0.34
    Activations Density 0.001%

    No Known Activations