© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 238727
    Prev
    Next
    INDEX
    Explanations

    sound alike or similar

    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_25_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
    пка
    0.43
     уже
    0.41
    жается
    0.40
    奇怪
    0.40
     ноябре
    0.40
    傈
    0.40
     hipert
    0.39
     infl
    0.39
     dí
    0.39
    lık
    0.39
    POSITIVE LOGITS
    engono
    0.40
    azze
    0.39
    les
    0.39
     find
    0.39
    aa
    0.39
    iami
    0.39
     besten
    0.39
    >';
    0.38
    iis
    0.38
    ermi
    0.38
    Activations Density 0.001%

    No Known Activations