© 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. 111648
    Prev
    Next
    INDEX
    Explanations

    conveying an idea

    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
    া
    0.92
    a
    0.91
    ।
    0.87
     (
    0.85
    an
    0.84
    erà
    0.84
    ה
    0.84
    ↵↵
    0.83
    。
    0.82
    อล
    0.82
    POSITIVE LOGITS
    т
    1.16
    ش
    1.14
    t
    1.06
    m
    1.04
    g
    1.00
    م
    1.00
     ouv
    0.99
     the
    0.96
    м
    0.92
    ן
    0.90
    Activations Density 0.007%

    No Known Activations