© 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. 122050
    Prev
    Next
    INDEX
    Explanations

    overall best presentation vision

    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
    iad
    0.76
    ت
    0.75
    ง
    0.62
     વેબસ
    0.61
     of
    0.60
    $
    0.60
     ylabel
    0.59
     b
    0.59
     at
    0.59
    takes
    0.55
    POSITIVE LOGITS
    ia
    0.69
    cje
    0.60
     dring
    0.59
    தி
    0.55
    kannya
    0.55
     convierten
    0.54
     inaction
    0.54
    cj
    0.52
    ình
    0.52
    ש
    0.52
    Activations Density 0.002%

    No Known Activations