© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50777
    Prev
    Next
    INDEX
    Explanations

    SQL code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    通
    0.80
    통
    0.73
     통
    0.66
     通
    0.61
     thông
    0.49
    に通
    0.48
     Tong
    0.47
     Thông
    0.43
    াউ
    0.39
    лід
    0.39
    POSITIVE LOGITS
     mode
    0.47
     之
    0.43
     valid
    0.42
     действу
    0.42
     gar
    0.40
     generally
    0.39
     aller
    0.39
     active
    0.38
    彬
    0.37
     ked
    0.37
    Activations Density 0.001%

    No Known Activations