© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58413
    Prev
    Next
    INDEX
    Explanations

    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_59_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
     ולא
    0.78
    を下
    0.55
    あ
    0.50
     জানান
    0.49
    まと
    0.41
     come
    0.37
     চাও
    0.37
     குடி
    0.35
     Ừ
    0.35
     Liqu
    0.35
    POSITIVE LOGITS
     دادن
    0.82
     وإ
    0.80
     گرفتن
    0.76
     کردن
    0.70
     والاست
    0.62
     شدن
    0.61
     داشتن
    0.54
     चुनने
    0.54
    を果た
    0.52
     رکھنے
    0.52
    Activations Density 0.003%

    No Known Activations