© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 102722
    Prev
    Next
    INDEX
    Explanations

    baseball cap

    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_1_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
    u
    1.65
    d
    1.47
    ।
    1.40
    ar
    1.34
    y
    1.32
    q
    1.30
    z
    1.22
    i
    1.20
    ad
    1.18
    स
    1.18
    POSITIVE LOGITS
    يك
    1.23
     vond
    1.10
    وي
    1.09
    ется
    1.08
     bude
    1.02
     cré
    1.02
    يا
    1.00
     adore
    1.00
    يري
    1.00
    يس
    0.99
    Activations Density 0.000%

    No Known Activations