© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33455
    Prev
    Next
    INDEX
    Explanations

    timestamps and separators

    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_40_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
     quatrième
    0.46
     ہوگی
    0.43
     ----------
    0.41
     மூன்ற
    0.41
     ④
    0.41
    ৪
    0.40
     fourth
    0.40
     Conc
    0.39
     कंड
    0.39
     चौथे
    0.37
    POSITIVE LOGITS
    <0xB2>
    0.50
                      
    0.49
    XVI
    0.43
    XVII
    0.42
    十二
    0.42
     microseconds
    0.41
     XVII
    0.41
     seventeenth
    0.38
     ज्यात
    0.38
     drenched
    0.37
    Activations Density 0.011%

    No Known Activations