© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 81867
    Prev
    Next
    INDEX
    Explanations

    add or sum to target

    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_29_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
     ର
    0.33
    向量
    0.32
     உட்க
    0.32
    fred
    0.32
     Prospects
    0.32
     consisted
    0.32
    ဘူး
    0.32
     Putra
    0.31
     conquered
    0.31
    .$;
    0.31
    POSITIVE LOGITS
    scene
    0.34
     lì
    0.33
    ্স
    0.32
     Shout
    0.32
     allí
    0.31
    ద్దు
    0.31
    scenes
    0.31
    regel
    0.31
     scène
    0.31
     Вайлдберриз
    0.30
    Activations Density 0.006%

    No Known Activations