© 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. 141754
    Prev
    Next
    INDEX
    Explanations

    case classes, componentN

    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
     굉장
    0.52
     情况
    0.50
     indústria
    0.49
    耑
    0.48
     prid
    0.48
    行业
    0.48
     accanto
    0.47
     เขา
    0.47
     الصنا
    0.47
     proguardFiles
    0.47
    POSITIVE LOGITS
    J
    0.63
    g
    0.53
     with
    0.50
    il
    0.50
    treated
    0.49
    г
    0.48
    ressive
    0.48
    я
    0.47
     maintained
    0.47
    い
    0.47
    Activations Density 0.002%

    No Known Activations