© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88731
    Prev
    Next
    INDEX
    Explanations

    freedom of speech

    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
    Negative Logits
    分子
    0.42
    Fifth
    0.41
    𝓽
    0.40
    都不
    0.39
    ूज
    0.38
     දී
    0.38
    но
    0.37
    िंट
    0.37
     ELECTRON
    0.37
    点
    0.37
    POSITIVE LOGITS
    il
    0.54
     бло
    0.46
    éli
    0.44
    eiros
    0.43
    ről
    0.43
    o
    0.43
    olisme
    0.43
    encher
    0.42
    ości
    0.42
     snippets
    0.42
    Activations Density 0.004%

    No Known Activations