© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49140
    Prev
    Next
    INDEX
    Explanations

    low

    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
     freezing
    0.68
     coldest
    0.63
    凍
    0.57
    冻
    0.54
     icy
    0.52
     freeze
    0.50
     chilly
    0.50
     colder
    0.49
    冷
    0.48
    freeze
    0.48
    POSITIVE LOGITS
     low
    2.36
    低
    2.17
    Low
    2.11
    low
    2.05
     Low
    2.02
     низ
    1.97
     低
    1.90
     LOW
    1.86
     düşük
    1.75
    LOW
    1.70
    Activations Density 0.016%

    No Known Activations