© 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. 79394
    Prev
    Next
    INDEX
    Explanations

    внешность compressor

    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
     intérêt
    1.42
     équip
    1.39
     arrête
    1.38
    ");
    1.34
     área
    1.34
    ش
    1.31
     avantage
    1.30
     étab
    1.29
     défin
    1.27
    "])
    1.27
    POSITIVE LOGITS
    s
    2.17
    ים
    2.00
     در
    1.54
    스가
    1.49
    들이
    1.44
    い
    1.43
    も
    1.38
    และ
    1.35
    いる
    1.34
    ς
    1.33
    Activations Density 0.000%

    No Known Activations