© 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. 156914
    Prev
    Next
    INDEX
    Explanations

    contracts and deals

    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
    Allan
    0.45
     Allan
    0.41
     இவை
    0.40
     Columb
    0.37
     Colomb
    0.37
     Johnstone
    0.37
    ურთიერთ
    0.36
    華
    0.36
     Tanah
    0.36
     Kinney
    0.35
    POSITIVE LOGITS
     saf
    0.41
     rhythmic
    0.40
     notifier
    0.40
     cy
    0.40
    шал
    0.40
    wys
    0.40
    Pw
    0.40
     stirring
    0.39
     minimalist
    0.39
     nutrition
    0.39
    Activations Density 0.000%

    No Known Activations