© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124392
    Prev
    Next
    INDEX
    Explanations

    experts and specific names like Gir/von/Ryan

    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_3_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
     rozwiąz
    0.86
    (
    0.80
     bagel
    0.61
     आ
    0.60
     разрабо
    0.59
     villas
    0.59
     confrontations
    0.59
     to
    0.58
     controllers
    0.57
     характеризу
    0.57
    POSITIVE LOGITS
    ৭১
    0.58
    N
    0.58
     is
    0.57
    um
    0.56
    T
    0.55
    ките
    0.55
    scode
    0.54
    ah
    0.54
    H
    0.54
    ပိုင်း
    0.54
    Activations Density 0.001%

    No Known Activations