© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206946
    Prev
    Next
    INDEX
    Explanations

    critique, accusation, description

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ={
    0.38
     newData
    0.37
    到现在
    0.37
     sectional
    0.37
     artyku
    0.35
     عربي
    0.34
     "~
    0.34
     نر
    0.34
     dati
    0.33
    ordial
    0.33
    POSITIVE LOGITS
     Completely
    0.37
     completely
    0.34
     브
    0.33
    completely
    0.33
     Boliv
    0.33
     Flip
    0.32
    αλ
    0.32
    insk
    0.32
     prepares
    0.31
     Lieferung
    0.31
    Activations Density 0.001%

    No Known Activations