© 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. 130596
    Prev
    Next
    INDEX
    Explanations

    buzzfeed quizzes

    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
    0
    1.59
    ى
    1.48
    an
    1.36
    c
    1.23
    r
    1.18
    <0x80>
    1.16
    ان
    1.15
    v
    1.14
    in
    1.10
    was
    1.10
    POSITIVE LOGITS
    ｸ
    1.13
     jedynie
    1.03
     aé
    1.01
    ｱ
    1.01
    का
    1.00
     aswell
    1.00
    ઠળ
    0.99
    .
    0.99
    ｺ
    0.98
     enthalpies
    0.96
    Activations Density 0.000%

    No Known Activations