© 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. 52319
    Prev
    Next
    INDEX
    Explanations

    say "l" words

    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
    下来
    0.40
     ছি
    0.38
    પુ
    0.37
    ieres
    0.35
    濡
    0.35
     গঠন
    0.34
     গঠিত
    0.34
    "{@
    0.34
     Consortium
    0.34
     hairdry
    0.34
    POSITIVE LOGITS
     bank
    0.75
    bank
    0.73
    Bank
    0.72
    银行
    0.69
    銀行
    0.69
     Bank
    0.68
     ngân
    0.67
    金融
    0.65
     BANK
    0.65
     банк
    0.65
    Activations Density 0.001%

    No Known Activations