© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77035
    Prev
    Next
    INDEX
    Explanations

    say "en" verbs

    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_53_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
    よかった
    0.43
    send
    0.40
     ladle
    0.38
     mel
    0.38
     tire
    0.38
    කිය
    0.38
     hinzuf
    0.37
     send
    0.36
    벨
    0.36
    笫
    0.36
    POSITIVE LOGITS
     оставить
    0.54
     zrobić
    0.46
    łączyć
    0.44
    зировать
    0.44
     написать
    0.42
     effettuare
    0.41
    isieren
    0.41
     привести
    0.41
     करना
    0.40
     использовать
    0.40
    Activations Density 0.001%

    No Known Activations