© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249563
    Prev
    Next
    INDEX
    Explanations

    word fragments

    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_56_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
    AE
    0.57
    а
    0.56
    Α
    0.54
    ɑ
    0.54
    ﺎ
    0.52
     AE
    0.52
    α
    0.50
    А
    0.50
    𝑎
    0.50
    ﺍ
    0.50
    POSITIVE LOGITS
     trp
    0.42
     Saran
    0.40
    䨘
    0.39
     カラ
    0.37
     Karak
    0.37
    主な
    0.37
     weer
    0.37
     appar
    0.37
     palette
    0.36
    ೆಯೇ
    0.36
    Activations Density 0.123%

    No Known Activations