© 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. 195556
    Prev
    Next
    INDEX
    Explanations

    City contexts

    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
    楊
    0.45
     Свя
    0.43
     Paw
    0.42
     vaso
    0.42
     Sarge
    0.40
     eingesch
    0.40
     Yang
    0.39
    卅
    0.39
     santa
    0.38
     Don
    0.38
    POSITIVE LOGITS
     புரா
    0.49
    Nem
    0.41
    Cent
    0.40
    通
    0.40
    City
    0.39
    Mirror
    0.39
    朝
    0.39
    роприя
    0.38
    Sunrise
    0.38
    Mir
    0.38
    Activations Density 0.002%

    No Known Activations