© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109555
    Prev
    Next
    INDEX
    Explanations

    insignificant, ensign

    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
    en
    1.70
    도
    1.54
    o
    1.53
    ا
    1.52
    त
    1.46
    ва
    1.45
    е
    1.39
    و
    1.39
    ar
    1.37
    ер
    1.37
    POSITIVE LOGITS
    ться
    1.38
    ’
    1.23
    1.07
    '
    1.04
    >
    1.01
    د
    0.98
     transpose
    0.95
    )。
    0.92
     standout
    0.91
     mezzanine
    0.90
    Activations Density 0.000%

    No Known Activations