© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157197
    Prev
    Next
    INDEX
    Explanations

    glacial

    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
     ")"
    0.40
     chas
    0.40
    zsche
    0.38
    Domestic
    0.35
     ফ্যা
    0.35
    悟
    0.35
    дай
    0.35
    azs
    0.35
    urten
    0.34
    azen
    0.34
    POSITIVE LOGITS
     freeze
    0.77
     hielo
    0.74
     ice
    0.74
     congel
    0.73
    freeze
    0.73
     frozen
    0.72
     Ice
    0.70
    冻
    0.70
     Freeze
    0.68
    凍
    0.68
    Activations Density 0.000%

    No Known Activations