© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15290
    Prev
    Next
    INDEX
    Explanations

    Mato Grosso, Cum, newEvent, buckwheat

    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_13_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
    BIND
    0.60
    ோ
    0.51
    FREQUENCY
    0.50
    BIC
    0.48
    ста
    0.47
    اک
    0.46
    їн
    0.46
    ITIONAL
    0.45
     DIFFICULTY
    0.45
    бан
    0.45
    POSITIVE LOGITS
    减
    0.47
    𝘶
    0.46
    之间
    0.45
    wość
    0.42
    kezi
    0.41
     Hause
    0.41
    时光
    0.40
    nea
    0.40
    先生
    0.40
    vc
    0.40
    Activations Density 0.001%

    No Known Activations