© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142731
    Prev
    Next
    INDEX
    Explanations

    mana cost, curve, or as energy

    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_0_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
    as
    1.78
    te
    1.36
    ו
    1.34
    '
    1.27
    が多く
    1.26
    us
    1.23
    ر
    1.23
    し
    1.22
    i
    1.19
    r
    1.16
    POSITIVE LOGITS
    ك
    1.70
    $
    1.62
    ة
    1.52
    ק
    1.50
     of
    1.48
    )。
    1.46
    ;
    1.39
    )
    1.38
    )，
    1.36
    是
    1.34
    Activations Density 0.000%

    No Known Activations