© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 151403
    Prev
    Next
    INDEX
    Explanations

    Catalan

    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_59_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
    Don
    0.57
     Don
    0.54
     pot
    0.51
     so
    0.48
     don
    0.46
    don
    0.45
     es
    0.38
    媒
    0.38
     is
    0.37
    Cin
    0.37
    POSITIVE LOGITS
     per
    0.42
     előtt
    0.40
     будете
    0.39
     были
    0.39
     थीं
    0.38
     haver
    0.38
     insuf
    0.37
     βρί
    0.37
     تُ
    0.37
     pró
    0.36
    Activations Density 0.003%

    No Known Activations