© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31286
    Prev
    Next
    INDEX
    Explanations

    <0xE3>

    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_7_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
    ↵
    0.68
    де
    0.50
     καθώς
    0.48
    σε
    0.48
    un
    0.47
     outperform
    0.47
     ۷
    0.46
    ਕ
    0.46
    im
    0.45
    um
    0.45
    POSITIVE LOGITS
     a
    0.78
     the
    0.60
     is
    0.58
    rotic
    0.52
    txt
    0.48
    רים
    0.45
    نا
    0.44
    ATA
    0.44
    נים
    0.44
    t
    0.43
    Activations Density 0.000%

    No Known Activations