© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11141
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     처
    0.40
    psi
    0.39
     chases
    0.38
    ปลาย
    0.38
    需要的
    0.37
     activated
    0.37
    Poor
    0.37
    lles
    0.36
    activated
    0.36
     sorte
    0.36
    POSITIVE LOGITS
    <0xB2>
    0.37
     کوډ
    0.37
    ன்க
    0.36
    dropBtn
    0.36
     Maxwell
    0.36
    糍
    0.35
     Bul
    0.35
     manuscripts
    0.34
     (!_
    0.34
     mannit
    0.34
    Activations Density 0.019%

    No Known Activations