© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217013
    Prev
    Next
    INDEX
    Explanations

    names and brands

    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_50_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
     W
    0.41
     WP
    0.39
     ファ
    0.39
     constituents
    0.39
    WU
    0.39
     frit
    0.39
     woodpe
    0.38
     WU
    0.37
     persistence
    0.36
    lanır
    0.36
    POSITIVE LOGITS
    亰
    0.42
     Hopefully
    0.40
    Moto
    0.40
     উড়িয়ে
    0.39
     تعالى
    0.39
     ters
    0.39
    bation
    0.38
     září
    0.38
    PHOTOS
    0.37
     मोती
    0.37
    Activations Density 0.000%

    No Known Activations