© 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
    2. Gemma-3-27B-IT
    3. 47-GEMMASCOPE-2-TRANSCODER-262K
    4. 213825
    Prev
    Next
    INDEX
    Explanations

    as

    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_47_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
     फेव
    0.48
    ্যতা
    0.40
    영어
    0.40
    БУ
    0.39
     Shih
    0.39
    ಆ
    0.39
    郆
    0.39
     ა
    0.38
    urare
    0.38
     Schuh
    0.37
    POSITIVE LOGITS
    glo
    0.42
    Spy
    0.38
     diverging
    0.37
    што
    0.37
    Olymp
    0.36
    Glo
    0.36
    allocate
    0.36
    theater
    0.35
    mdi
    0.35
    Galer
    0.35
    Activations Density 0.001%

    No Known Activations