© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39397
    Prev
    Next
    INDEX
    Explanations

    ES, PY, PA sequence

    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_3_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
    T
    0.83
    I
    0.79
    cción
    0.74
    kont
    0.72
    that
    0.71
     Ελλάδα
    0.71
    Hound
    0.70
    W
    0.70
    </b>
    0.67
    '
    0.67
    POSITIVE LOGITS
    ي
    1.15
    י
    1.12
    א
    1.09
    a
    1.08
    is
    0.87
    ق
    0.86
    מ
    0.82
    ע
    0.81
    ت
    0.80
    া
    0.79
    Activations Density 0.004%

    No Known Activations