© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243051
    Prev
    Next
    INDEX
    Explanations

    I know, I say, you do

    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_40_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
     inevitably
    0.40
     항상
    0.40
     always
    0.37
     봤
    0.37
     şeyler
    0.37
     всегда
    0.36
    سین
    0.36
    したが
    0.35
    ellular
    0.35
     saw
    0.34
    POSITIVE LOGITS
     прекра
    0.41
    icoli
    0.39
    vaient
    0.39
    त्र
    0.37
    빼
    0.37
     роботи
    0.37
    問題を
    0.37
    ப்போ
    0.36
    iria
    0.36
    leaning
    0.35
    Activations Density 0.006%

    No Known Activations