© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161841
    Prev
    Next
    INDEX
    Explanations

    ewing, money, audit, percent

    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_2_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
    ot
    1.22
    for
    1.22
    as
    1.20
    an
    1.09
    AR
    1.05
     for
    1.02
    (
    0.99
    il
    0.97
    ar
    0.95
    For
    0.93
    POSITIVE LOGITS
    u
    1.59
    و
    1.59
    ו
    1.59
    ی
    1.50
    ہ
    1.35
    s
    1.34
    ের
    1.23
    ים
    1.21
    ли
    1.16
    ні
    1.13
    Activations Density 0.000%

    No Known Activations