© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84135
    Prev
    Next
    INDEX
    Explanations

    тем, чтобы

    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_0_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
    ۳
    1.55
    é
    1.49
    um
    1.48
    uje
    1.45
    ın
    1.45
    ates
    1.41
    و
    1.40
    amid
    1.38
    ക്ക്
    1.37
    atkar
    1.36
    POSITIVE LOGITS
    ח
    1.76
    نا
    1.67
    ش
    1.59
    ס
    1.59
    ج
    1.55
    ك
    1.52
    ني
    1.48
    স
    1.45
    ג
    1.41
     be
    1.37
    Activations Density 0.000%

    No Known Activations