© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211046
    Prev
    Next
    INDEX
    Explanations

    district ending

    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_5_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
    predictors
    0.65
    are
    0.64
    0.64
     و
    0.61
    uv
    0.61
     نحو
    0.59
    physiological
    0.58
     not
    0.58
    affer
    0.56
    accessor
    0.56
    POSITIVE LOGITS
    ש
    1.14
    ك
    1.08
    on
    1.05
    ди
    0.96
    ב
    0.96
    la
    0.94
    са
    0.91
    يت
    0.86
    ด
    0.85
    લ
    0.84
    Activations Density 0.001%

    No Known Activations