© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58127
    Prev
    Next
    INDEX
    Explanations

    funny bone

    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_11_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
     conduit
    0.51
    Ι
    0.51
    ජ
    0.50
    thane
    0.47
     esso
    0.47
     conduits
    0.47
    {$
    0.46
     resident
    0.46
    êts
    0.45
     inflater
    0.45
    POSITIVE LOGITS
    चानक
    0.50
    وڑا
    0.50
    sü
    0.49
    ானது
    0.48
    APER
    0.47
    ಗೂ
    0.47
    iselt
    0.47
    ısına
    0.46
    篌
    0.46
    냐면
    0.46
    Activations Density 0.000%

    No Known Activations