© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144561
    Prev
    Next
    INDEX
    Explanations

    respectful

    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_0_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
    s
    2.50
    ים
    2.03
    ی
    1.97
    a
    1.89
    ों
    1.87
    ς
    1.84
     that
    1.74
    ।
    1.63
    д
    1.60
    ם
    1.59
    POSITIVE LOGITS
    1.64
    ारा
    1.12
    $
    1.09
    িল
    1.08
    ess
    1.05
    illä
    1.05
    arien
    1.05
     +:+
    1.04
    ہ
    1.03
    ash
    1.02
    Activations Density 0.004%

    No Known Activations