© 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. 216611
    Prev
    Next
    INDEX
    Explanations

    Richard Stallman

    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
    Arrow
    0.41
    ሁን
    0.40
    িয়ন
    0.40
    嚨
    0.39
    F
    0.39
     F
    0.38
     Arrow
    0.38
    ፍ
    0.38
     Ф
    0.37
     الف
    0.37
    POSITIVE LOGITS
    pou
    0.43
     trade
    0.43
    Pou
    0.43
     nep
    0.43
     Kg
    0.39
    Beng
    0.39
    trade
    0.39
     Pou
    0.39
     TRADE
    0.39
     Blank
    0.38
    Activations Density 0.002%

    No Known Activations