© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 211740
    Prev
    Next
    INDEX
    Explanations

    post

    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_43_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
    EFF
    0.39
    useEffect
    0.38
     manda
    0.37
     useEffect
    0.37
    နည်း
    0.37
    Feb
    0.36
    ጉ
    0.35
     Pathways
    0.35
    niają
    0.35
    舉
    0.35
    POSITIVE LOGITS
     mort
    1.70
    Mort
    1.67
     Mort
    1.61
    mort
    1.59
     mortality
    1.55
     MORT
    1.51
     mortal
    1.48
     Mortality
    1.34
     mortar
    1.34
     Mortal
    1.34
    Activations Density 0.001%

    No Known Activations