© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42569
    Prev
    Next
    INDEX
    Explanations

    Survey Corps

    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_13_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
    ijker
    0.45
     wounds
    0.44
    酸
    0.43
    Calls
    0.43
     slowest
    0.42
     hardships
    0.42
     calorías
    0.42
    ک
    0.41
     scratches
    0.41
    ockets
    0.40
    POSITIVE LOGITS
    banding
    0.49
    paration
    0.46
    活跃
    0.44
    tooltip
    0.44
     sebagaimana
    0.44
     представитель
    0.44
    反对
    0.43
    转发
    0.43
    棪
    0.43
    fär
    0.42
    Activations Density 0.001%

    No Known Activations