© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 30397
    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_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
     Dalton
    0.43
    Cas
    0.43
     writer
    0.42
    Rud
    0.41
     Gerald
    0.40
    ገድ
    0.40
     escribe
    0.40
    細
    0.40
    Coh
    0.39
     Getty
    0.38
    POSITIVE LOGITS
     avoided
    0.52
     avoiding
    0.48
     avoid
    0.46
    avoid
    0.44
    Avoid
    0.43
     tránh
    0.42
     avoids
    0.41
     قلب
    0.41
    避免
    0.40
    NLP
    0.39
    Activations Density 0.011%

    No Known Activations