© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205692
    Prev
    Next
    INDEX
    Explanations

    controlled strings or sentences

    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_20_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
    thisobject
    0.03
     generalised
    0.03
     chlorides
    0.03
     convexo
    0.03
    Suspend
    0.03
     enqueue
    0.03
    ัพ
    0.03
     tetrachloride
    0.03
    镁
    0.03
    Missense
    0.03
    POSITIVE LOGITS
     We
    0.03
    heim
    0.03
    rare
    0.03
    fl
    0.03
    protected
    0.03
     Sche
    0.03
     R
    0.03
     L
    0.03
     &
    0.03
     over
    0.02
    Activations Density 0.153%

    No Known Activations