© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39599
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    e
    0.91
    s
    0.82
    x
    0.74
     minimize
    0.67
    ﺭ
    0.67
     prioritize
    0.67
     oxidize
    0.63
    .
    0.63
     maximize
    0.60
     حالة
    0.60
    POSITIVE LOGITS
     It
    1.01
    یک
    0.96
     to
    0.95
    کش
    0.93
    یت
    0.91
    ۰
    0.89
    ید
    0.85
    یس
    0.83
    کم
    0.83
    습니다
    0.82
    Activations Density 0.000%

    No Known Activations