© 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
    2. Gemma-3-27B-IT
    3. 29-GEMMASCOPE-2-TRANSCODER-262K
    4. 80811
    Prev
    Next
    INDEX
    Explanations

    0g

    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_29_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
    смотря
    0.42
    मेट
    0.39
    宻
    0.38
    ্যান
    0.38
    сматри
    0.38
    ohist
    0.38
    abelian
    0.37
    d
    0.37
    贵
    0.36
    অভ
    0.36
    POSITIVE LOGITS
     kj
    0.43
     Plus
    0.38
     flag
    0.38
     Basketball
    0.38
     GM
    0.37
     continued
    0.36
    TakePhoto
    0.36
     Peso
    0.36
     Grande
    0.35
     Continued
    0.35
    Activations Density 0.001%

    No Known Activations