© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21958
    Prev
    Next
    INDEX
    Explanations

    language fragments

    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_56_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
    y
    0.42
    রিক
    0.39
     tension
    0.37
     tensions
    0.37
    ości
    0.37
    وفيق
    0.36
    ernetes
    0.36
     জন্মদিন
    0.35
    ু
    0.35
     visually
    0.35
    POSITIVE LOGITS
    er
    0.46
    kapet
    0.43
     পাকিস্ত
    0.42
    ffle
    0.41
    eah
    0.39
    ishi
    0.39
    chaften
    0.39
    eh
    0.38
    esinin
    0.37
    lications
    0.37
    Activations Density 0.008%

    No Known Activations