© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132984
    Prev
    Next
    INDEX
    Explanations

    at

    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
     ლი
    0.40
     đàn
    0.36
     angered
    0.36
     സ
    0.36
    များကို
    0.36
    (@"
    0.36
    တီ
    0.34
    ]-
    0.34
    量の
    0.34
    轩
    0.34
    POSITIVE LOGITS
     implicitly
    0.48
     implicit
    0.47
     Implicit
    0.46
     gust
    0.45
     SIGNIFIC
    0.44
    Gust
    0.43
    Implicit
    0.40
    磧
    0.39
     whirl
    0.39
     explicitly
    0.38
    Activations Density 0.006%

    No Known Activations