© 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. 212506
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    r
    1.81
    s
    1.52
    at
    1.38
    ra
    1.36
    er
    1.35
    า
    1.34
    he
    1.33
    ling
    1.31
    ar
    1.30
    ing
    1.30
    POSITIVE LOGITS
    ج
    1.19
    شك
    1.18
    ને
    1.17
    ش
    1.16
    جين
    1.15
    ص
    1.15
    ס
    1.13
    جلس
    1.10
    ملك
    1.09
    جري
    1.08
    Activations Density 0.000%

    No Known Activations