© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260920
    Prev
    Next
    INDEX
    Explanations

    resonate

    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_5_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
    να
    0.84
    ب
    0.79
    لية
    0.79
    loten
    0.78
    لز
    0.77
    риев
    0.76
    бль
    0.74
    ხვევ
    0.74
     على
    0.73
     وأ
    0.73
    POSITIVE LOGITS
    v
    1.45
    1
    1.07
    0
    1.00
    ing
    0.96
    ü
    0.96
    f
    0.95
    8
    0.89
    se
    0.86
    n
    0.85
    í
    0.84
    Activations Density 0.001%

    No Known Activations