© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50481
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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_55_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
     logging
    0.44
     Logging
    0.43
    نظر
    0.38
    CIÓN
    0.37
     Visual
    0.36
    "]);
    0.35
     Vista
    0.35
    logging
    0.35
     logged
    0.35
     peace
    0.34
    POSITIVE LOGITS
    发育
    0.37
    বাত
    0.36
     নিয়মিত
    0.36
    栻
    0.36
     Konrad
    0.36
    procedures
    0.36
    Assured
    0.35
    atmospheric
    0.35
    閤
    0.35
    अच्छ
    0.35
    Activations Density 0.004%

    No Known Activations