© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12007
    Prev
    Next
    INDEX
    Explanations

    you just

    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
     ≈
    0.50
     аб
    0.45
     عب
    0.43
     роз
    0.40
    飏
    0.40
     الب
    0.40
     соціа
    0.40
    }):=\
    0.39
     дли
    0.38
     інте
    0.38
    POSITIVE LOGITS
    en
    0.66
    u
    0.64
    n
    0.62
    7
    0.61
    1
    0.56
    5
    0.56
    r
    0.55
    3
    0.55
    E
    0.55
    9
    0.55
    Activations Density 0.055%

    No Known Activations