© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 121380
    Prev
    Next
    INDEX
    Explanations

    jQuery document ready and click events

    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_38_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
    vió
    0.40
     する
    0.39
    尌
    0.38
    şan
    0.38
     него
    0.38
    ಾರಿ
    0.37
     riduzione
    0.36
    fileobj
    0.36
    மிய
    0.36
    汔
    0.35
    POSITIVE LOGITS
    new
    0.51
     جدید
    0.49
     new
    0.45
     новую
    0.43
     ಹೊಸ
    0.43
    新
    0.42
     nouveaux
    0.42
     নতুন
    0.42
     새로
    0.41
     новом
    0.40
    Activations Density 0.000%

    No Known Activations