© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207051
    Prev
    Next
    INDEX
    Explanations

    .file or .files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
     androidTest
    0.50
    rusty
    0.48
     savent
    0.46
    ច្រើន
    0.45
     głównie
    0.45
     ፕሮ
    0.45
    倝
    0.45
    nian
    0.44
     dynast
    0.44
     baptized
    0.43
    POSITIVE LOGITS
     effects
    0.54
    Students
    0.47
     امتیاز
    0.46
    ت
    0.46
     değişiklik
    0.45
    Effects
    0.44
     تغییر
    0.44
    Laundry
    0.43
    effects
    0.43
    変更
    0.42
    Activations Density 0.002%

    No Known Activations