© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212053
    Prev
    Next
    INDEX
    Explanations

    psionic/psoriatic suffixation

    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
    ز
    1.17
    க
    1.04
    વ
    1.00
    the
    0.98
    자
    0.97
     sebag
    0.96
    ad
    0.93
    ड
    0.92
    ୦
    0.91
    ท
    0.91
    POSITIVE LOGITS
    ↵
    1.27
     as
    1.25
    ↵↵
    1.15
    、
    1.15
    ム
    1.04
    لي
    1.03
    ný
    1.03
    ung
    1.00
    ną
    0.98
     but
    0.98
    Activations Density 0.000%

    No Known Activations