© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47280
    Prev
    Next
    INDEX
    Explanations

    best results

    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
     g
    0.50
     bombardment
    0.45
     dioxide
    0.44
     shrub
    0.42
     bacterial
    0.41
     t
    0.40
     bitch
    0.40
     GHG
    0.39
     o
    0.39
     drab
    0.38
    POSITIVE LOGITS
    2
    0.61
    4
    0.51
    ك
    0.48
    Dé
    0.46
    да
    0.45
    Де
    0.44
    Noir
    0.44
    8
    0.44
    드
    0.44
    Опера
    0.43
    Activations Density 0.003%

    No Known Activations