© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80946
    Prev
    Next
    INDEX
    Explanations

    endorphins

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     inoxidable
    0.40
    overwrite
    0.38
    旨在
    0.36
     concreto
    0.35
    ೊಳ
    0.35
     overwrite
    0.35
    Puzzle
    0.35
    욱
    0.35
    ಳ
    0.34
    inak
    0.34
    POSITIVE LOGITS
    \".
    0.46
    ').
    0.45
    ”).
    0.41
    țional
    0.40
     ”.
    0.40
    \",
    0.40
     ").
    0.39
     directly
    0.38
    \")
    0.38
    ’).
    0.38
    Activations Density 0.005%

    No Known Activations