© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112229
    Prev
    Next
    INDEX
    Explanations

    light scattering

    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_2_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
    y
    1.23
    t
    1.15
    k
    1.15
    d
    1.09
    the
    1.04
    на
    1.03
    to
    1.02
    ,
    0.98
    is
    0.97
    েও
    0.97
    POSITIVE LOGITS
     in
    1.19
     δύο
    0.98
    のは
    0.95
     よく
    0.91
     در
    0.89
     บอก
    0.84
     ਨਾਲ
    0.83
     sumptuous
    0.82
     tanggal
    0.81
     انتہائی
    0.80
    Activations Density 0.000%

    No Known Activations