© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132886
    Prev
    Next
    INDEX
    Explanations

    software and finance

    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_50_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
    Bigr
    0.43
    heder
    0.42
    াহার
    0.41
    aih
    0.41
    よび
    0.40
    Ꭹ
    0.40
     FULLER
    0.38
    اہ
    0.37
    愠
    0.37
    inales
    0.37
    POSITIVE LOGITS
    enci
    0.43
     tái
    0.43
    anted
    0.42
    мани
    0.42
     man
    0.41
    স্থিত
    0.39
     tố
    0.38
     අධ
    0.38
     Recycle
    0.38
     Disc
    0.38
    Activations Density 0.060%

    No Known Activations