© 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. 203561
    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
    𝕄
    0.39
     particulate
    0.39
     რომ
    0.37
     Abe
    0.36
     moh
    0.36
     aid
    0.35
    IRONMENT
    0.35
     Máy
    0.35
     Moh
    0.35
     sack
    0.35
    POSITIVE LOGITS
     Sulfur
    0.41
     കാരണ
    0.38
    getStudentNo
    0.38
     zar
    0.38
    getUsername
    0.37
    免
    0.37
    Azur
    0.37
     Bedrooms
    0.36
    Might
    0.35
     szüks
    0.35
    Activations Density 0.000%

    No Known Activations