© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87079
    Prev
    Next
    INDEX
    Explanations

    open weights download inspect use

    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_23_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
    MSS
    0.39
     ች
    0.39
     зал
    0.38
     средство
    0.37
     TimeUnit
    0.35
    ንዳ
    0.35
     空
    0.34
     glassy
    0.34
    空格
    0.34
     aço
    0.34
    POSITIVE LOGITS
    േഷൻ
    0.43
     Persona
    0.41
    န်း
    0.41
     비롯
    0.40
    Chang
    0.39
    г
    0.39
    崔
    0.39
    ेंद्रीय
    0.38
    ❋
    0.38
     Democrat
    0.38
    Activations Density 0.007%

    No Known Activations