© 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. 129619
    Prev
    Next
    INDEX
    Explanations

    pyramids

    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
    า
    1.31
    ন
    0.98
     enem
    0.95
    ับ
    0.93
    ออก
    0.93
    os
    0.91
     osob
    0.91
    อะไร
    0.89
     প্রকৌশ
    0.89
    ைகள்
    0.88
    POSITIVE LOGITS
    ні
    1.11
    <0xA6>
    1.02
    ین
    1.00
    ro
    0.99
    ق
    0.94
    ي
    0.92
    ;
    0.90
    res
    0.88
    él
    0.88
    <0xB7>
    0.88
    Activations Density 0.000%

    No Known Activations