© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37228
    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_57_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
    간
    0.40
     تیر
    0.39
    wohner
    0.38
     gn
    0.38
     खूब
    0.37
    haft
    0.37
     ma
    0.37
    间
    0.37
    avkh
    0.36
    maat
    0.36
    POSITIVE LOGITS
     Ve
    0.38
     siger
    0.35
     confes
    0.35
     уни
    0.35
    ኔ
    0.34
     vein
    0.34
     Envoy
    0.34
     Cheat
    0.34
     коро
    0.33
     warns
    0.33
    Activations Density 0.000%

    No Known Activations