© 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. 232241
    Prev
    Next
    INDEX
    Explanations

    brunch

    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
    to
    1.05
    ່ນ
    0.97
    కు
    0.93
    P
    0.92
    日数
    0.92
    да
    0.91
    सामान्यीकृत
    0.91
    em
    0.91
    giờ
    0.89
    もので
    0.88
    POSITIVE LOGITS
    ת
    1.26
     I
    1.21
    ل
    1.16
    ล
    1.16
    ร
    1.09
    м
    0.99
    тни
    0.92
    ur
    0.91
    I
    0.89
     U
    0.87
    Activations Density 0.000%

    No Known Activations