© 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
    2. Gemma-3-27B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 48546
    Prev
    Next
    INDEX
    Explanations

    people interacting with systems

    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_10_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
    0.32
    ні
    0.30
    ।
    0.30
    ،
    0.28
    🏠
    0.27
    ។
    0.26
    )$
    0.25
    🎁
    0.25
     Comune
    0.25
     substituents
    0.25
    POSITIVE LOGITS
     zabud
    0.29
    ul
    0.28
     går
    0.27
     dvě
    0.27
    into
    0.27
    izados
    0.27
     zwei
    0.27
    intos
    0.27
     noget
    0.26
     gente
    0.26
    Activations Density 0.025%

    No Known Activations