© 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
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203499
    Prev
    Next
    INDEX
    Explanations

    language and settings

    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_12_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
    1
    1.02
    2
    0.96
     from
    0.82
    ONE
    0.80
     ON
    0.78
     on
    0.77
     weeks
    0.74
    ON
    0.73
    6
    0.73
     two
    0.67
    POSITIVE LOGITS
    ితీ
    0.77
    楎
    0.71
     Еўропы
    0.69
    峼
    0.69
     পূর্ববাংলা
    0.67
    舩
    0.66
    綪
    0.66
     বিটিআই
    0.64
    લ્લા
    0.64
    仠
    0.63
    Activations Density 0.055%

    No Known Activations