© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231453
    Prev
    Next
    INDEX
    Explanations

    knowledge distillation

    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_6_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
    é
    1.66
    }
    1.13
    ad
    1.05
    ant
    1.03
    ate
    1.02
    ade
    1.01
    á
    0.98
    al
    0.97
    0.97
    ay
    0.95
    POSITIVE LOGITS
    ן
    1.18
    া
    1.13
    т
    1.05
    ﺖ
    1.02
    یا
    0.96
    לות
    0.95
    Tổng
    0.92
    𝗹
    0.91
    니다
    0.91
     Tử
    0.91
    Activations Density 0.000%

    No Known Activations