© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 67041
    Prev
    Next
    INDEX
    Explanations

    say importance levels

    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_46_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
    Low
    0.82
     low
    0.80
    low
    0.71
    低
    0.71
     Low
    0.69
     düşük
    0.68
     низ
    0.65
    LOW
    0.64
     低
    0.63
     LOW
    0.62
    POSITIVE LOGITS
    ၎
    0.42
     ওয়া
    0.40
     Сред
    0.39
     sred
    0.38
    ჯერ
    0.38
    infix
    0.37
    middleware
    0.37
    eces
    0.37
    रन
    0.37
     сред
    0.36
    Activations Density 0.014%

    No Known Activations