© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30254
    Prev
    Next
    INDEX
    Explanations

    injection, injected, needles, syringes

    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_10_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
    (
    0.63
    ته
    0.59
    unov
    0.56
    imbo
    0.54
    ientos
    0.52
    imax
    0.52
    atien
    0.52
    ets
    0.52
    unay
    0.51
    ethe
    0.51
    POSITIVE LOGITS
     injecting
    0.73
     inject
    0.65
     injections
    0.64
    针
    0.64
     injection
    0.61
    Inject
    0.59
     needles
    0.59
     injected
    0.57
    י
    0.57
     Injection
    0.57
    Activations Density 0.030%

    No Known Activations