© 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
    2. Gemma-3-27B-IT
    3. 37-GEMMASCOPE-2-TRANSCODER-262K
    4. 124160
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
     shr
    0.42
     focus
    0.39
     residing
    0.37
     understood
    0.35
    Pul
    0.35
    矣
    0.35
     oh
    0.34
     OH
    0.34
    可能な
    0.34
     안전
    0.34
    POSITIVE LOGITS
     Abubakar
    0.40
     Abub
    0.39
    switchTo
    0.37
    ෑ
    0.37
     Ruben
    0.37
     Massimo
    0.36
    campus
    0.35
     plunge
    0.35
     Kamer
    0.35
     Nicki
    0.35
    Activations Density 0.000%

    No Known Activations