© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78388
    Prev
    Next
    INDEX
    Explanations

    vendors

    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_0_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
     to
    1.77
    ৫
    1.05
     de
    1.01
    bied
    1.01
    .
    0.99
    ාවිත
    0.98
    kaan
    0.98
     sheath
    0.98
     likeness
    0.98
     mandala
    0.97
    POSITIVE LOGITS
    ق
    2.38
    다
    2.09
    B
    1.86
    e
    1.81
    ك
    1.80
    ва
    1.76
    D
    1.73
    ي
    1.73
    a
    1.73
    ات
    1.72
    Activations Density 0.001%

    No Known Activations