© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26685
    Prev
    Next
    INDEX
    Explanations

    writing a story

    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_10_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
    ร์
    0.43
    та
    0.40
    л
    0.39
    า
    0.38
    ك
    0.38
    м
    0.33
    к
    0.33
    தேச
    0.32
    ন
    0.31
    ва
    0.31
    POSITIVE LOGITS
    .
    0.31
    にし
    0.29
     क्वेश्चन
    0.29
    ylan
    0.29
    GLOBALS
    0.29
     branca
    0.28
    Panic
    0.28
    钤
    0.28
     सुरेंद्र
    0.28
    InputNum
    0.27
    Activations Density 0.016%

    No Known Activations