© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 57612
    Prev
    Next
    INDEX
    Explanations

    Eiffel Tower

    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_2_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
     was
    1.47
     to
    1.43
    н
    1.31
    <0x0D>
    1.26
     chunks
    1.14
     gás
    1.13
     compositor
    1.12
     not
    1.11
     malicious
    1.11
    n
    1.11
    POSITIVE LOGITS
    f
    1.54
    、
    1.18
    ק
    1.16
    Red
    1.14
    ك
    1.14
    ری
    1.13
    rest
    1.13
    fact
    1.12
    на
    1.11
    2
    1.09
    Activations Density 0.013%

    No Known Activations