© 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. 199118
    Prev
    Next
    INDEX
    Explanations

    Chinese titles and names

    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
    -
    0.64
     இரண்டாவது
    0.57
     darken
    0.56
     serpentine
    0.54
    ka
    0.54
    cel
    0.53
    <0xAB>
    0.52
    met
    0.52
     purposeful
    0.52
    йда
    0.49
    POSITIVE LOGITS
    법
    0.66
    ্টে
    0.59
    ۳
    0.59
    edited
    0.57
    Matcher
    0.56
     Likes
    0.55
     Journal
    0.54
     아니라
    0.54
     Etc
    0.54
     Irina
    0.54
    Activations Density 0.002%

    No Known Activations