© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22744
    Prev
    Next
    INDEX
    Explanations

    and

    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_56_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
    One
    0.44
     One
    0.43
    And
    0.37
     หนึ่ง
    0.37
    郢
    0.36
     And
    0.36
    AND
    0.35
    ವಿಲ್ಲ
    0.35
    one
    0.34
    ativi
    0.34
    POSITIVE LOGITS
     En
    1.46
    En
    1.36
     en
    1.20
     EN
    1.16
     ен
    0.97
     эн
    0.91
     엔
    0.89
    エン
    0.87
    èn
    0.86
    EN
    0.85
    Activations Density 0.012%

    No Known Activations