© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170688
    Prev
    Next
    INDEX
    Explanations

    indicating origin

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     із
    1.18
     outta
    1.01
     daraus
    0.96
     ze
    0.95
     из
    0.93
     зі
    0.91
     з
    0.82
     din
    0.82
     z
    0.81
     spo
    0.76
    POSITIVE LOGITS
     от
    0.52
    થી
    0.41
    live
    0.38
    от
    0.38
    पासून
    0.35
    विजन
    0.35
    От
    0.34
    ய்டா
    0.34
    perplexity
    0.34
     من
    0.34
    Activations Density 0.003%

    No Known Activations