© 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. 36224
    Prev
    Next
    INDEX
    Explanations

    names

    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
    grand
    0.41
    یتی
    0.40
    Vel
    0.39
    ंगर
    0.39
    Taylor
    0.39
     rejuvenated
    0.39
    Whitney
    0.38
    ⊙
    0.38
    ওয়া
    0.37
    princess
    0.37
    POSITIVE LOGITS
     Edwin
    0.50
     Ed
    0.46
    Ed
    0.45
     Par
    0.44
     Cosmo
    0.43
    ner
    0.42
    Edwin
    0.41
     parabol
    0.41
    תו
    0.38
     Toshiba
    0.38
    Activations Density 0.001%

    No Known Activations