© 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. 5154
    Prev
    Next
    INDEX
    Explanations

    diagonal elements

    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
     আশ্রয়
    0.38
     imidazol
    0.38
     parameters
    0.37
     emptiness
    0.37
     parâmetros
    0.37
    挙
    0.37
    ূন্য
    0.35
    ユー
    0.35
     versed
    0.35
     verse
    0.34
    POSITIVE LOGITS
    FileAlignment
    0.44
     Blocks
    0.41
     Courts
    0.41
     കോടതി
    0.40
    Bishop
    0.40
    panda
    0.39
    Brandon
    0.39
    ❙
    0.39
    blocks
    0.38
     Brandon
    0.38
    Activations Density 0.012%

    No Known Activations