© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 207022
    Prev
    Next
    INDEX
    Explanations

    what kind of you

    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_25_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
    yorum
    0.31
     אני
    0.31
     댓글
    0.30
     ప్రతి
    0.30
     אות
    0.30
    ):["
    0.29
     انا
    0.29
     பிரச்ச
    0.29
     مشکل
    0.28
    我相信
    0.28
    POSITIVE LOGITS
    色が
    0.27
    সে
    0.27
    ꒳
    0.27
    прежнему
    0.26
    Pine
    0.26
     வண்ணம்
    0.24
     Rogue
    0.24
     tuttavia
    0.24
    豐富
    0.24
    เริ่มต้น
    0.24
    Activations Density 0.003%

    No Known Activations