© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33213
    Prev
    Next
    INDEX
    Explanations

    explores concepts

    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_31_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
    الل
    0.18
     মুজিব
    0.17
     abhor
    0.17
     sharpen
    0.17
     학
    0.16
     ghost
    0.16
    也許
    0.16
     literally
    0.16
     arguably
    0.16
     Moro
    0.16
    POSITIVE LOGITS
    '^
    0.17
     assaulting
    0.17
    ட்டு
    0.17
    ariya
    0.17
     "'";
    0.16
     lanjutan
    0.16
    遒
    0.16
    arsa
    0.16
     Clicking
    0.16
    ろしく
    0.16
    Activations Density 0.368%

    No Known Activations