© 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. 31360
    Prev
    Next
    INDEX
    Explanations

    consider sponsorship

    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
    ระ
    0.34
     stav
    0.33
     außer
    0.31
     dins
    0.31
     Petersburg
    0.31
     travaillé
    0.31
    เลี้ยง
    0.31
    ৃ
    0.31
    Հ
    0.31
    ૐ
    0.30
    POSITIVE LOGITS
    ുമു
    0.40
     proposition
    0.38
     tempted
    0.36
     bù
    0.35
     temptation
    0.33
    BBB
    0.33
    bb
    0.33
    诱
    0.33
     tempt
    0.32
    挲
    0.32
    Activations Density 0.031%

    No Known Activations