© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233559
    Prev
    Next
    INDEX
    Explanations

    based on experience

    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_32_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
    庤
    0.39
    ajemen
    0.37
     नाकाम
    0.37
     histograms
    0.35
    ]$,
    0.35
     قناه
    0.35
     ни
    0.35
    )`,
    0.35
     siglos
    0.34
    Printing
    0.34
    POSITIVE LOGITS
     wellness
    0.43
     मांगी
    0.40
     Require
    0.39
    測定
    0.36
     shifting
    0.36
     Wellness
    0.35
     requiring
    0.35
     shortages
    0.35
     Duff
    0.35
     YANG
    0.35
    Activations Density 0.000%

    No Known Activations