© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77735
    Prev
    Next
    INDEX
    Explanations

    people

    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_53_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
     H
    0.51
     اله
    0.47
    H
    0.45
    Ｈ
    0.45
    एच
    0.42
     এইচ
    0.40
     ہ
    0.40
    ሾ
    0.39
     एच
    0.39
     दूस
    0.39
    POSITIVE LOGITS
    innie
    0.45
     کنید
    0.42
    Ker
    0.41
    ontium
    0.41
    istungen
    0.41
     pound
    0.41
     zirconia
    0.38
    Decimal
    0.38
     چیک
    0.38
     DSA
    0.38
    Activations Density 0.000%

    No Known Activations