© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220541
    Prev
    Next
    INDEX
    Explanations

    argparse

    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_31_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
    фии
    0.36
     нещо
    0.36
     πό
    0.36
    왠
    0.36
     decision
    0.36
     missing
    0.36
    Decision
    0.36
    Чу
    0.35
    lil
    0.35
    야
    0.35
    POSITIVE LOGITS
     Trom
    0.43
    पूर्व
    0.38
     răng
    0.37
     دھو
    0.37
    octopus
    0.37
     أق
    0.37
    মতী
    0.37
    懟
    0.36
     trom
    0.34
     Gameplay
    0.33
    Activations Density 0.000%

    No Known Activations