© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13392
    Prev
    Next
    INDEX
    Explanations

    skin tone fair pale clear

    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_13_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
    мати
    0.43
    湿
    0.43
    ความ
    0.43
    ذة
    0.43
    وار
    0.42
    :
    0.40
    ру
    0.40
    ля
    0.39
    Splash
    0.39
    р
    0.39
    POSITIVE LOGITS
     CRO
    0.43
     proportional
    0.42
     Kahn
    0.41
    propane
    0.41
     unscrupulous
    0.40
    iono
    0.40
     Johnston
    0.40
     prophetic
    0.40
     preposition
    0.39
     prophets
    0.39
    Activations Density 0.084%

    No Known Activations