© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5655
    Prev
    Next
    INDEX
    Explanations

    run

    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_44_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
    riumph
    0.39
     بندی
    0.38
    合物
    0.38
    Ę
    0.38
     মাদ
    0.38
    skinned
    0.37
    疯
    0.37
    кович
    0.36
     strapping
    0.36
     găsit
    0.36
    POSITIVE LOGITS
    ofa
    0.41
    QRY
    0.40
    辙
    0.38
     επα
    0.37
    iterrows
    0.37
     Pho
    0.36
     True
    0.36
     Luka
    0.35
     MeV
    0.35
     Phon
    0.34
    Activations Density 0.002%

    No Known Activations