© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223267
    Prev
    Next
    INDEX
    Explanations

    at best

    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
    m
    0.37
    in
    0.33
     in
    0.32
     브
    0.31
     fiume
    0.30
     در
    0.30
    ain
    0.29
     차량
    0.29
    osta
    0.28
     Слу
    0.28
    POSITIVE LOGITS
    7
    0.36
    8
    0.35
    9
    0.33
    2
    0.33
    0
    0.32
    1
    0.30
    För
    0.29
    Alic
    0.29
    Information
    0.29
    Editorial
    0.29
    Activations Density 0.001%

    No Known Activations