© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61701
    Prev
    Next
    INDEX
    Explanations

    verbs following articles and pronouns

    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_11_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
    dH
    0.60
    dioxide
    0.56
    drum
    0.54
    ០
    0.54
    播
    0.54
    dor
    0.52
    dB
    0.52
    展望
    0.52
    dP
    0.50
    dé
    0.48
    POSITIVE LOGITS
    i
    0.65
    ي
    0.64
     устра
    0.59
     update
    0.58
     przetwarz
    0.58
     upd
    0.57
     güncelle
    0.55
     outpouring
    0.55
     output
    0.54
     avion
    0.54
    Activations Density 0.009%

    No Known Activations