© 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. 36150
    Prev
    Next
    INDEX
    Explanations

    artifact, competition, attack, models, truth, system, team, offensive, Foundation

    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
    Politics
    0.32
    subseteq
    0.32
     नयी
    0.30
    Wend
    0.29
     у
    0.29
    politics
    0.29
    婇
    0.29
    Star
    0.28
    更多
    0.28
     Women
    0.28
    POSITIVE LOGITS
    稞
    0.36
     breach
    0.31
     DAYS
    0.30
     conseguenza
    0.30
    ındaki
    0.30
     marcha
    0.29
     semanas
    0.29
    INAL
    0.29
     дней
    0.29
    靘
    0.29
    Activations Density 0.025%

    No Known Activations