© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64787
    Prev
    Next
    INDEX
    Explanations

    the quadratic formula

    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_41_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
    ħ
    0.46
    ROHAN
    0.41
    ucer
    0.39
    美人
    0.38
    romax
    0.38
     Girona
    0.38
     механи
    0.38
    ({{
    0.38
    (\{
    0.38
    рома
    0.38
    POSITIVE LOGITS
    Quantitative
    0.40
     햇
    0.40
     quantitative
    0.38
     Quantitative
    0.37
     관
    0.37
     사용
    0.37
     ingres
    0.36
     completos
    0.36
     taping
    0.36
    用い
    0.36
    Activations Density 0.002%

    No Known Activations