© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2802
    Prev
    Next
    INDEX
    Explanations

    database errors

    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_40_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
     connecté
    0.39
    спек
    0.38
    რულ
    0.38
    connectivity
    0.38
    Curves
    0.37
     conexão
    0.36
    ᖇ
    0.36
    魯
    0.36
    uffix
    0.36
    SETUP
    0.36
    POSITIVE LOGITS
     Current
    0.47
     Vickers
    0.41
     Apply
    0.38
     current
    0.37
     dehydrogen
    0.37
    太平
    0.37
    Current
    0.35
     پیشہ
    0.34
     resol
    0.34
     artificial
    0.34
    Activations Density 0.000%

    No Known Activations