© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 92094
    Prev
    Next
    INDEX
    Explanations

    dietary habits

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    d
    0.83
    t
    0.73
    s
    0.71
     of
    0.68
     مؤرشف
    0.67
     Auflage
    0.67
    profits
    0.66
                    
    0.65
    of
    0.65
    et
    0.64
    POSITIVE LOGITS
    ל
    0.68
    لی
    0.65
    ק
    0.64
    กับการ
    0.60
     niiden
    0.60
    ین
    0.60
    .?
    0.60
    ור
    0.58
    กับ
    0.58
    ¹.
    0.58
    Activations Density 0.001%

    No Known Activations