© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100943
    Prev
    Next
    INDEX
    Explanations

    possibility and negation

    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_14_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
    з
    0.37
    м
    0.37
    ज
    0.36
    may
    0.35
    <0x0D>
    0.35
     may
    0.34
    п
    0.34
     later
    0.31
     dowol
    0.31
     if
    0.31
    POSITIVE LOGITS
    致力
    0.36
     ഇഷ്ട
    0.31
    ्रिया
    0.29
    ೇತ್ರ
    0.29
    ោ
    0.29
    hui
    0.29
    ennzeichnet
    0.28
    itories
    0.28
     グ
    0.28
     Наде
    0.28
    Activations Density 0.113%

    No Known Activations