© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48259
    Prev
    Next
    INDEX
    Explanations

    inner dialog

    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_31_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
     لفظ
    0.38
    ૂ
    0.38
    泯
    0.37
    ('''
    0.37
     insisted
    0.36
     apologized
    0.36
     demanded
    0.36
    獗
    0.36
     overcrowded
    0.35
     crowded
    0.35
    POSITIVE LOGITS
     internally
    0.51
     secretly
    0.51
    Internal
    0.48
    Planning
    0.48
     सोच
    0.46
    Thinking
    0.44
     सोचते
    0.44
     silently
    0.43
    Intern
    0.42
     Thinking
    0.42
    Activations Density 0.058%

    No Known Activations