© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210973
    Prev
    Next
    INDEX
    Explanations

    This is

    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_20_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
    硣
    0.45
     disseminating
    0.43
     прогре
    0.42
    COTT
    0.41
     অগ্রগতি
    0.41
     வருக
    0.40
     просмотра
    0.40
     LIKE
    0.38
     dissemination
    0.38
     щ
    0.38
    POSITIVE LOGITS
     or
    0.48
    ak
    0.47
    ות
    0.47
     veya
    0.46
    ัง
    0.46
     Many
    0.44
    льная
    0.44
     różne
    0.43
    av
    0.42
    or
    0.42
    Activations Density 0.004%

    No Known Activations