© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64050
    Prev
    Next
    INDEX
    Explanations

    take

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    充电
    0.39
    ɲ
    0.39
    жээ
    0.38
    }^{-\
    0.38
     charged
    0.37
    Charged
    0.37
    êté
    0.37
     charging
    0.37
    🏷
    0.37
    驩
    0.37
    POSITIVE LOGITS
     জিনিসের
    0.46
     вещей
    0.43
     things
    0.40
    icaria
    0.40
     apart
    0.38
    除了
    0.38
     Sachen
    0.38
     জিনিস
    0.38
    GraphicsUnit
    0.38
     Vita
    0.37
    Activations Density 0.002%

    No Known Activations