© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90224
    Prev
    Next
    INDEX
    Explanations

    process stages

    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_11_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
    ли
    0.57
    安
    0.55
    αν
    0.55
    ολ
    0.55
    기
    0.50
    なし
    0.49
    家
    0.49
     iodide
    0.49
    σ
    0.48
    नि
    0.47
    POSITIVE LOGITS
     diez
    0.59
    itaire
    0.58
     смотреть
    0.58
     took
    0.57
     schme
    0.56
    ätz
    0.56
     termasuk
    0.55
     jangan
    0.55
    istä
    0.55
    ützen
    0.55
    Activations Density 0.028%

    No Known Activations