© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37799
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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_57_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
     tivemos
    0.43
     }:
    0.41
    一旦
    0.39
    
    0.39
    िवेदी
    0.38
    Pause
    0.37
    留意
    0.36
     paused
    0.36
    IGO
    0.36
     pause
    0.36
    POSITIVE LOGITS
     Ses
    0.49
    待
    0.47
     ses
    0.47
    Ses
    0.46
     SES
    0.39
     certa
    0.38
     пока
    0.37
    ไหน
    0.36
    害
    0.36
    няют
    0.35
    Activations Density 0.003%

    No Known Activations