© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 137277
    Prev
    Next
    INDEX
    Explanations

    late 20th century

    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_37_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
    aceus
    0.36
    чених
    0.36
    のアレンジ
    0.35
     ட
    0.35
    どう
    0.35
     આપ
    0.35
    Hyper
    0.35
     ریلی
    0.35
    アレンジ
    0.34
     cep
    0.34
    POSITIVE LOGITS
     late
    0.48
    晚
    0.46
     बॉर्डर
    0.41
     Late
    0.40
    late
    0.39
     tanh
    0.39
     beve
    0.38
    elapse
    0.38
     larg
    0.37
     ture
    0.37
    Activations Density 0.002%

    No Known Activations