© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 196716
    Prev
    Next
    INDEX
    Explanations

    speech recognition and concentration

    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_15_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
    ai
    0.57
     subconsciously
    0.53
    ed
    0.51
     haut
    0.50
     recursively
    0.50
    Ꮒ
    0.49
     subtly
    0.48
    ıkları
    0.48
     `-
    0.48
    es
    0.46
    POSITIVE LOGITS
     तेल
    0.50
    オイル
    0.48
    匣
    0.48
     Portug
    0.46
    キン
    0.45
     polos
    0.45
     conversar
    0.45
     কথোপ
    0.44
     وتع
    0.44
    stå
    0.44
    Activations Density 0.000%

    No Known Activations