© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199427
    Prev
    Next
    INDEX
    Explanations

    able

    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_50_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
    簸
    0.38
    .].
    0.37
    icz
    0.36
     Associations
    0.36
    Elsewhere
    0.36
     Wilbur
    0.36
    ।]
    0.36
     Nevertheless
    0.36
     স্নাত
    0.35
    তথ
    0.35
    POSITIVE LOGITS
     mark
    0.42
    लोकन
    0.42
    landish
    0.42
    keyboard
    0.41
    теры
    0.41
    ISTAN
    0.40
     dashes
    0.39
    ኤ
    0.39
    ব্লিউ
    0.39
    कोल
    0.39
    Activations Density 0.002%

    No Known Activations