© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 242194
    Prev
    Next
    INDEX
    Explanations

    add to favorites, playlist, cart

    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_25_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
    נע
    0.35
     subtraction
    0.34
    互動
    0.33
     す
    0.32
    ض
    0.32
    РИ
    0.32
     rotational
    0.31
    thaus
    0.31
    ж
    0.31
    ILT
    0.31
    POSITIVE LOGITS
     পাগল
    0.39
     manier
    0.38
    otipos
    0.37
     ಆಯ್
    0.36
     deceduto
    0.36
    ˬ
    0.36
    Caprio
    0.36
    熟悉的
    0.35
    毫无
    0.35
     inéd
    0.34
    Activations Density 0.000%

    No Known Activations