© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209729
    Prev
    Next
    INDEX
    Explanations

    though it

    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_5_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
    0
    1.34
    9
    1.07
     I
    1.06
     that
    1.02
    ää
    1.01
    ij
    1.00
     with
    0.99
    ین
    0.99
     که
    0.98
    n
    0.97
    POSITIVE LOGITS
    ка
    1.41
    ৫
    1.33
    า
    1.32
    的
    1.24
    ను
    1.17
    ко
    1.15
    at
    1.13
    ные
    1.12
    اك
    1.11
    會
    1.10
    Activations Density 0.002%

    No Known Activations