© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57998
    Prev
    Next
    INDEX
    Explanations

    that the

    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_11_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
    화
    0.35
    해
    0.34
    화를
    0.33
    was
    0.32
    Ia
    0.32
    валась
    0.32
    вался
    0.31
     pequeños
    0.31
    었습니다
    0.31
    φέρον
    0.31
    POSITIVE LOGITS
     اینکه
    0.36
    g
    0.36
    ’
    0.34
    အရေ
    0.34
    inin
    0.33
    le
    0.31
    )}$
    0.31
     اندازه
    0.31
    m
    0.31
    िएगा
    0.31
    Activations Density 0.026%

    No Known Activations