© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229461
    Prev
    Next
    INDEX
    Explanations

    digging

    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_6_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
    O
    1.01
    w
    0.96
    ل
    0.82
     arou
    0.82
     Áng
    0.80
     allgeme
    0.79
    પ
    0.79
    كتب
    0.79
     invalidate
    0.79
    ন
    0.77
    POSITIVE LOGITS
    ні
    0.99
    و
    0.99
    ம்
    0.91
    ↵
    0.79
     stringent
    0.77
    ษัท
    0.73
    된
    0.71
    ៥
    0.71
     व
    0.71
     მისი
    0.71
    Activations Density 0.000%

    No Known Activations