© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17510
    Prev
    Next
    INDEX
    Explanations

    equations and calculations

    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_34_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
     Munt
    0.43
    தொ
    0.40
    Mitt
    0.39
    Sak
    0.38
     Mitt
    0.37
    সভা
    0.37
    ḳ
    0.37
     Sak
    0.37
     Ibrahim
    0.36
     Arif
    0.36
    POSITIVE LOGITS
    运
    0.42
    蕪
    0.38
    運
    0.38
     mandarin
    0.36
    岸
    0.35
    aciones
    0.35
     diretamente
    0.35
    تباينه
    0.34
     गोयल
    0.34
     Noida
    0.34
    Activations Density 0.006%

    No Known Activations