© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80078
    Prev
    Next
    INDEX
    Explanations

    say "-"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     (-
    2.28
     $(-
    2.09
     (−
    2.02
    (-
    1.91
     [-
    1.90
    (−
    1.75
     (-)
    1.74
    }(-
    1.73
     `-
    1.70
     $[-
    1.70
    POSITIVE LOGITS
     Kult
    0.41
    滄
    0.40
    utton
    0.38
     Puls
    0.38
     bull
    0.38
     Oliv
    0.37
     vệ
    0.37
    ufig
    0.37
    extras
    0.37
    滞
    0.36
    Activations Density 0.007%

    No Known Activations