© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129594
    Prev
    Next
    INDEX
    Explanations

    ils

    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_1_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
    ל
    1.36
    า
    1.09
    قي
    1.07
    и
    1.05
    ن
    1.02
    น
    1.01
    ,
    1.00
    IN
    0.99
    ص
    0.98
    ิ
    0.96
    POSITIVE LOGITS
    1
    1.47
    s
    1.27
    t
    1.04
     at
    0.98
     for
    0.96
     taxa
    0.94
    ため
    0.92
    er
    0.92
    یی
    0.92
    ell
    0.90
    Activations Density 0.000%

    No Known Activations