© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 244626
    Prev
    Next
    INDEX
    Explanations

    well architected

    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
     нар
    0.42
     ¶
    0.41
    सौ
    0.38
     paragraph
    0.36
     historical
    0.36
    新区
    0.36
     First
    0.36
     ப
    0.35
     Primeira
    0.35
     []*
    0.35
    POSITIVE LOGITS
     соответ
    0.38
     bertujuan
    0.38
     enforced
    0.38
    或许
    0.37
    Rather
    0.37
    Politics
    0.37
    Choose
    0.36
    ਿਆਂ
    0.36
     صفحات
    0.36
     enforce
    0.36
    Activations Density 0.002%

    No Known Activations