© 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. 36612
    Prev
    Next
    INDEX
    Explanations

    life balance

    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
    ו
    0.80
    ك
    0.70
     queries
    0.66
     returns
    0.66
    ዣ
    0.65
     dar
    0.64
     replies
    0.63
     η
    0.63
    のリ
    0.62
    ка
    0.60
    POSITIVE LOGITS
    is
    1.09
    يل
    1.00
    g
    0.85
    s
    0.84
    ط
    0.79
    ación
    0.76
    p
    0.76
    d
    0.75
    c
    0.74
    can
    0.73
    Activations Density 0.016%

    No Known Activations