© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136146
    Prev
    Next
    INDEX
    Explanations

    steep terrain

    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_12_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
    绯
    0.52
    '];
    0.50
     Göl
    0.49
    classList
    0.49
     ILLINOIS
    0.49
    莎
    0.48
     වැ
    0.48
     Zentral
    0.47
     odred
    0.47
     STOR
    0.46
    POSITIVE LOGITS
    binom
    0.63
    rem
    0.60
    him
    0.59
    dzi
    0.56
    hi
    0.55
    omb
    0.54
     coroner
    0.54
    ό
    0.54
    kw
    0.53
    मर
    0.53
    Activations Density 0.003%

    No Known Activations