© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257189
    Prev
    Next
    INDEX
    Explanations

    Should I, motivation, flow, print

    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_22_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
    🙃
    0.43
    ቀም
    0.42
     homelessness
    0.41
    ریح
    0.41
     sker
    0.40
    หล
    0.40
     homeless
    0.40
    (($
    0.40
    🤞
    0.39
    کریاں
    0.39
    POSITIVE LOGITS
     Biod
    0.40
     protege
    0.40
    anchen
    0.39
    zip
    0.39
    책
    0.39
     முழு
    0.38
     expectativa
    0.38
    ores
    0.38
     छोटा
    0.38
     Ein
    0.38
    Activations Density 0.000%

    No Known Activations