© 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. 212916
    Prev
    Next
    INDEX
    Explanations

    wallet

    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
    م
    1.39
    ↵↵
    1.30
    تو
    1.25
    ט
    1.23
    خ
    1.22
    ات
    1.18
    िया
    1.06
    ك
    1.02
    انت
    0.96
    ین
    0.91
    POSITIVE LOGITS
    a
    1.56
    o
    1.39
    L
    1.19
    N
    1.16
    ा
    1.16
    dır
    1.13
    PAPER
    1.13
    ના
    1.10
    TINGS
    1.10
    RIGHT
    1.08
    Activations Density 0.000%

    No Known Activations