© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65788
    Prev
    Next
    INDEX
    Explanations

    names

    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_46_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
    Battery
    0.40
    蘼
    0.38
     району
    0.37
    sqlUpdate
    0.36
    mapper
    0.36
    फोल
    0.36
     Battery
    0.36
     سایټ
    0.35
    <0x18>
    0.35
    পুন
    0.35
    POSITIVE LOGITS
     Ahmed
    0.59
     Ahmad
    0.58
     Singh
    0.57
     Mishra
    0.57
     Williams
    0.57
     Rodriguez
    0.54
     Sánchez
    0.54
     अहमद
    0.53
     Rodríguez
    0.52
     Mohamed
    0.52
    Activations Density 0.003%

    No Known Activations