© 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. 212662
    Prev
    Next
    INDEX
    Explanations

    comparison

    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
    ใน
    1.44
    K
    1.41
    ও
    1.37
     in
    1.36
    在
    1.36
    v
    1.23
    Y
    1.08
    나
    1.07
    KING
    1.05
    AN
    1.02
    POSITIVE LOGITS
    ем
    1.59
    ب
    1.27
    ות
    1.20
    ض
    1.20
    تي
    1.16
    ت
    1.16
    oz
    1.13
    تين
    1.13
    ת
    1.13
     gewisse
    1.09
    Activations Density 0.005%

    No Known Activations