© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136923
    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
     comfort
    0.39
    ença
    0.39
    代
    0.38
    CTT
    0.37
    Comfort
    0.37
    Rh
    0.36
     Comfort
    0.36
    颠
    0.35
    Dry
    0.35
     Rh
    0.34
    POSITIVE LOGITS
    聞き
    0.43
     Quatre
    0.42
     uname
    0.42
     overnight
    0.41
    hours
    0.41
     educa
    0.40
     heures
    0.40
     bleue
    0.39
     প্রচারণা
    0.39
     horas
    0.39
    Activations Density 0.000%

    No Known Activations