© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 118187
    Prev
    Next
    INDEX
    Explanations

    potential risk or chance

    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
    이에요
    0.42
     бути
    0.41
     Ê
    0.41
     стало
    0.40
     fraud
    0.39
     oldu
    0.39
     trùng
    0.38
    ಾಗಿದೆ
    0.38
     होगी
    0.38
     προβ
    0.38
    POSITIVE LOGITS
     ಬಳಸ
    0.38
     پہنچ
    0.36
     menerapkan
    0.36
     වඩා
    0.36
    ക്കോ
    0.35
     powering
    0.35
     \\[
    0.35
     utilizan
    0.35
     conducts
    0.35
    hasa
    0.35
    Activations Density 0.005%

    No Known Activations