© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135545
    Prev
    Next
    INDEX
    Explanations

    satisfactory, ability

    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_6_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
     (
    1.09
    t
    1.08
     ampli
    1.06
     indic
    1.00
     expon
    0.92
     muros
    0.91
     reorgan
    0.89
    B
    0.88
     toDo
    0.88
     peptid
    0.87
    POSITIVE LOGITS
    1.13
     सप्टेंबर
    1.01
    سی
    0.95
    ika
    0.94
    $
    0.93
    he
    0.92
    บ
    0.92
    ح
    0.89
    ש
    0.88
    ל
    0.88
    Activations Density 0.022%

    No Known Activations