© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57399
    Prev
    Next
    INDEX
    Explanations

    AI, politics, programming

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     gerecht
    0.36
    হইতে
    0.35
     veineux
    0.32
    ")):
    0.32
    锼
    0.32
     অনুয
    0.32
     animaux
    0.31
    ைகளை
    0.31
    elser
    0.31
     भीड़
    0.31
    POSITIVE LOGITS
    <0xC2>
    0.50
    َ
    0.38
    \,
    0.38
     ‌
    0.36
    َص
    0.36
     **
    0.36
                    
    0.35
    ঙ
    0.35
     |=
    0.35
     _
    0.35
    Activations Density 0.079%

    No Known Activations