© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31336
    Prev
    Next
    INDEX
    Explanations

    parentheses punctuation follow

    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
     DSS
    0.44
     економі
    0.41
    暹
    0.40
    ﺪ
    0.38
     údaj
    0.38
    സി
    0.38
    域名
    0.37
     Udaipur
    0.37
     كلهم
    0.35
     كافة
    0.35
    POSITIVE LOGITS
    ismar
    0.44
    clicked
    0.39
     revise
    0.39
    riven
    0.38
    amt
    0.37
    inim
    0.36
    abhavam
    0.36
    捒
    0.36
     yaparak
    0.36
    aruhi
    0.35
    Activations Density 0.021%

    No Known Activations