© 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. 35349
    Prev
    Next
    INDEX
    Explanations

    specific items

    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
    式の
    0.46
     Ability
    0.44
     Approach
    0.41
     একের
    0.41
     ability
    0.39
    跏
    0.38
     Translations
    0.38
     চারটি
    0.38
    Dictionaries
    0.38
     বিষয়টা
    0.38
    POSITIVE LOGITS
    們
    0.45
     huge
    0.42
     hefty
    0.39
     original
    0.38
     entire
    0.38
     official
    0.38
    ەکانی
    0.38
     hasty
    0.37
     porous
    0.37
     veritable
    0.36
    Activations Density 0.138%

    No Known Activations