© 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. 81354
    Prev
    Next
    INDEX
    Explanations

    cartoon called

    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
    માં
    1.48
    u
    1.47
    ların
    1.44
    ہ
    1.42
    
    1.33
    ﺔ
    1.32
    ی
    1.28
    ﮑ
    1.28
     incentivize
    1.27
    t
    1.22
    POSITIVE LOGITS
    Z
    1.79
    M
    1.61
    ت
    1.48
    T
    1.47
    D
    1.41
    E
    1.41
    B
    1.37
    )।
    1.36
    W
    1.35
    P
    1.34
    Activations Density 0.001%

    No Known Activations