© 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. 33267
    Prev
    Next
    INDEX
    Explanations

    introversion vs extraversion

    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
    _{+}$
    0.38
     dum
    0.36
     Meister
    0.36
     hace
    0.36
    适合
    0.35
    priority
    0.35
    perception
    0.35
     projectors
    0.34
     Cham
    0.34
     luft
    0.34
    POSITIVE LOGITS
     ಎ
    0.41
    ংক
    0.40
     ऊपरी
    0.40
    中间
    0.38
     escol
    0.37
    井
    0.37
    Mag
    0.37
    埃
    0.37
     jac
    0.36
    जात
    0.35
    Activations Density 0.015%

    No Known Activations