© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168647
    Prev
    Next
    INDEX
    Explanations

    letters

    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_34_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
     GW
    0.28
     Nai
    0.27
     ሂደ
    0.26
     biofuel
    0.26
    ipher
    0.26
     Gud
    0.26
    撑
    0.26
    Workflow
    0.25
    (/(
    0.25
    Though
    0.24
    POSITIVE LOGITS
    中です
    0.32
     کاب
    0.28
    lichting
    0.28
     cabo
    0.27
    となります
    0.27
    paw
    0.27
     remise
    0.26
     paw
    0.26
    embangan
    0.26
    caa
    0.26
    Activations Density 0.000%

    No Known Activations