© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108588
    Prev
    Next
    INDEX
    Explanations

    través de

    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_2_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
    에
    1.16
     d
    1.12
    ٥
    1.07
    9
    1.06
    all
    1.02
    ן
    1.02
    MY
    0.97
    స్‌
    0.96
     on
    0.95
     HAS
    0.95
    POSITIVE LOGITS
    ف
    1.42
    '
    1.41
    ب
    1.25
    م
    1.23
    হ
    1.19
    大
    1.17
    ق
    1.16
    ج
    1.05
    เป็น
    1.05
    位置
    0.98
    Activations Density 0.001%

    No Known Activations