© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201298
    Prev
    Next
    INDEX
    Explanations

    angels and cherubic beings

    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_12_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
    天使
    0.70
     Angels
    0.64
    С
    0.60
    Ре
    0.58
    Projekt
    0.57
    👼
    0.55
     Warszawie
    0.55
    '
    0.54
     Gottes
    0.54
    Для
    0.53
    POSITIVE LOGITS
    hus
    0.53
     endangering
    0.52
     acids
    0.52
    s
    0.51
     overlaid
    0.50
    olds
    0.49
     coches
    0.48
     никакого
    0.48
    isuus
    0.48
    zca
    0.48
    Activations Density 0.002%

    No Known Activations