© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121748
    Prev
    Next
    INDEX
    Explanations

    power source

    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_3_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
    ﺍ
    0.63
    と
    0.62
    清新
    0.60
    ブランド
    0.59
    限定
    0.59
    }}
    0.58
    オン
    0.58
    B
    0.58
    <0x0D>
    0.58
    }`);
    0.57
    POSITIVE LOGITS
    س
    0.61
    स
    0.59
    с
    0.58
    ны
    0.57
    ג
    0.57
    го
    0.55
    ك
    0.55
    力的
    0.52
     Sovere
    0.52
    oves
    0.52
    Activations Density 0.002%

    No Known Activations