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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76813
    Prev
    Next
    INDEX
    Explanations

    take it

    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_31_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
    絓
    0.40
    க்கால்
    0.40
     юк
    0.39
    莪
    0.38
    载
    0.36
     रोज़
    0.36
    捏
    0.35
     Okinawa
    0.35
    肖
    0.35
     Или
    0.34
    POSITIVE LOGITS
     spatially
    0.40
     travaux
    0.39
     colonia
    0.39
     met
    0.39
     colonial
    0.39
    colonial
    0.38
     subcl
    0.38
     colon
    0.38
     identificado
    0.38
    Density
    0.37
    Activations Density 0.001%

    No Known Activations