© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34627
    Prev
    Next
    INDEX
    Explanations

    URLs and websites

    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_50_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
     T
    0.41
    冕
    0.39
    ﻘ
    0.39
    ﻔ
    0.38
    夰
    0.37
    **,
    0.37
     boomers
    0.37
     abortions
    0.36
     న
    0.36
    Ded
    0.36
    POSITIVE LOGITS
     K
    0.63
     الك
    0.51
     ک
    0.49
     К
    0.44
     Κ
    0.41
     Six
    0.41
     六
    0.39
     SIX
    0.38
    K
    0.38
    ্টা
    0.37
    Activations Density 0.021%

    No Known Activations