© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43498
    Prev
    Next
    INDEX
    Explanations

    water window dream

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    خ
    0.91
    ك
    0.87
    ن
    0.86
    ج
    0.85
    2
    0.82
    ס
    0.80
    ות
    0.78
    ون
    0.77
    ية
    0.76
    คุณ
    0.68
    POSITIVE LOGITS
    t
    1.00
    r
    0.77
     इसे
    0.64
    もら
    0.63
    いました
    0.58
    d
    0.56
    tal
    0.54
    tor
    0.53
    ía
    0.52
     investigação
    0.52
    Activations Density 0.038%

    No Known Activations