© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141602
    Prev
    Next
    INDEX
    Explanations

    Carrington, Fulton, Monroe

    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
    is
    1.79
    ي
    1.70
    يلي
    1.66
    هي
    1.66
     وي
    1.64
    يارات
    1.49
    ينا
    1.48
    يئة
    1.41
    يق
    1.36
    小
    1.34
    POSITIVE LOGITS
    ی
    1.76
    ک
    1.70
    ین
    1.45
    ید
    1.42
    تی
    1.40
    سی
    1.38
    ों
    1.32
    ים
    1.31
    the
    1.27
    ifting
    1.21
    Activations Density 0.000%

    No Known Activations