© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199084
    Prev
    Next
    INDEX
    Explanations

    greeting "hi"

    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_27_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
     orgull
    0.43
    槁
    0.39
    تما
    0.39
    unan
    0.38
    luoromethyl
    0.36
    સ્થા
    0.36
    꼈
    0.36
     ادارے
    0.36
     appellee
    0.35
     orgullo
    0.35
    POSITIVE LOGITS
    আজ
    0.43
     типи
    0.36
    ===
    0.36
     tipped
    0.36
    abu
    0.35
     TICK
    0.35
    殺
    0.35
    説
    0.35
    Libra
    0.35
     suicides
    0.34
    Activations Density 0.003%

    No Known Activations