© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10624
    Prev
    Next
    INDEX
    Explanations

    Generation Type

    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_13_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
    fans
    0.49
    l
    0.48
    মাত্রা
    0.48
     Rectangle
    0.48
    ალი
    0.47
    attached
    0.47
     fans
    0.46
    face
    0.46
    ('/')
    0.44
    我們先
    0.44
    POSITIVE LOGITS
     cuál
    0.54
     encerr
    0.54
     pueden
    0.52
     preparando
    0.52
    Ngày
    0.51
     বইটি
    0.51
     Puedes
    0.51
     dadurch
    0.51
     sospe
    0.51
     Pode
    0.51
    Activations Density 0.016%

    No Known Activations