© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245720
    Prev
    Next
    INDEX
    Explanations

    python function definitions

    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_40_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
    ান্তি
    0.40
    解決
    0.39
     নেন
    0.37
    ઉ
    0.36
     menulis
    0.36
     scrivere
    0.36
    PrototypeOf
    0.36
    dynamical
    0.35
    鉭
    0.35
     McQu
    0.35
    POSITIVE LOGITS
    abria
    0.44
     recus
    0.40
    def
    0.38
     Forrest
    0.37
    딩
    0.37
    趼
    0.36
    юз
    0.36
    gue
    0.36
    èm
    0.35
    yang
    0.35
    Activations Density 0.004%

    No Known Activations