© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80607
    Prev
    Next
    INDEX
    Explanations

    Baltimore, Maryland

    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
     Clarence
    0.45
     budgeted
    0.38
     jon
    0.37
     खो
    0.37
     Metro
    0.36
     mam
    0.36
    clf
    0.36
     ে
    0.36
     nan
    0.35
     кла
    0.35
    POSITIVE LOGITS
    SECUR
    0.43
     দেখতে
    0.41
    यला
    0.40
    pwd
    0.39
    Leng
    0.39
    paris
    0.38
    iada
    0.37
     পুরুষের
    0.37
    Nick
    0.37
     Toc
    0.37
    Activations Density 0.000%

    No Known Activations