© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207442
    Prev
    Next
    INDEX
    Explanations

    in

    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_46_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
     good
    0.40
     same
    0.39
     whole
    0.38
    »)
    0.38
    serialized
    0.38
    serde
    0.37
     property
    0.37
    __)
    0.37
    мыми
    0.37
    мець
    0.37
    POSITIVE LOGITS
     aumentar
    0.56
     erhöhen
    0.55
     aumenta
    0.54
     افزایش
    0.53
     meningkat
    0.51
     증가
    0.51
     збіль
    0.50
     poveć
    0.50
     tăng
    0.49
     erhöht
    0.49
    Activations Density 0.002%

    No Known Activations