© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48638
    Prev
    Next
    INDEX
    Explanations

    here is

    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_10_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
    ک
    0.76
    া
    0.70
    Q
    0.70
    C
    0.69
    N
    0.69
    জ
    0.69
     avoir
    0.68
    мию
    0.68
    두
    0.67
    یت
    0.66
    POSITIVE LOGITS
    ad
    0.74
     ១
    0.69
    bibinfo
    0.66
    apixel
    0.66
     他
    0.64
     pivoted
    0.58
    <unused85>
    0.58
     .)
    0.58
     .
    0.57
     subcl
    0.57
    Activations Density 0.001%

    No Known Activations