© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212649
    Prev
    Next
    INDEX
    Explanations

    storage units and facilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_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
    ن
    1.90
    ন
    1.71
    न
    1.61
    น
    1.50
    н
    1.34
    ン
    1.31
    an
    1.23
    ν
    1.20
    ر
    1.16
    ↵↵
    1.14
    POSITIVE LOGITS
    uje
    0.95
    하다
    0.95
     encargado
    0.89
    меча
    0.89
    ление
    0.87
    ور
    0.83
     colocadas
    0.83
    ﻮ
    0.80
    kannya
    0.79
    くない
    0.77
    Activations Density 0.007%

    No Known Activations