© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28927
    Prev
    Next
    INDEX
    Explanations

    he, here, hey, yo

    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
     Buscar
    0.72
    ى
    0.70
    a
    0.69
    리
    0.68
     sbag
    0.66
    ه
    0.66
     quadrada
    0.66
     বলিব
    0.65
     Zas
    0.64
     I
    0.64
    POSITIVE LOGITS
    ucking
    0.69
     to
    0.61
    ång
    0.60
    вається
    0.60
     требования
    0.59
    9
    0.58
     ironing
    0.58
     разде
    0.55
     don
    0.55
     osteoporosis
    0.55
    Activations Density 0.021%

    No Known Activations