© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239102
    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_25_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
     cytoplasmic
    0.49
     propensity
    0.49
     abrasion
    0.46
    ֆ
    0.46
    হ্য
    0.46
     normative
    0.45
     procedural
    0.45
     deont
    0.45
     MV
    0.44
     decom
    0.44
    POSITIVE LOGITS
     zweiten
    0.56
    تي
    0.55
     Dienste
    0.54
     zweite
    0.52
     to
    0.50
     업
    0.50
    zej
    0.48
    Directors
    0.48
     Businesses
    0.47
     Menteri
    0.47
    Activations Density 0.000%

    No Known Activations