© 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. 132776
    Prev
    Next
    INDEX
    Explanations

    language and information

    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
     র
    0.42
    Linki
    0.42
     LINKS
    0.41
    穩
    0.40
     Rfd
    0.40
     ر
    0.39
    umur
    0.39
    UM
    0.39
     r
    0.38
     TE
    0.37
    POSITIVE LOGITS
     Palmer
    0.40
     margins
    0.39
    дер
    0.38
     sante
    0.38
     Lazarus
    0.37
     anto
    0.37
     мета
    0.37
     प्रसाद
    0.36
    ópez
    0.36
    Der
    0.36
    Activations Density 0.000%

    No Known Activations