© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 145190
    Prev
    Next
    INDEX
    Explanations

    numbers followed by parenthesis

    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_18_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
    事
    0.46
    排序
    0.44
    ţi
    0.43
     Asoci
    0.42
     Tur
    0.42
    पछि
    0.42
    䉽
    0.41
    DZ
    0.41
    াঃ
    0.41
    とされる
    0.40
    POSITIVE LOGITS
    cèle
    0.47
     revenues
    0.47
     boilers
    0.45
    adoo
    0.44
     maniac
    0.44
    iguing
    0.43
     próxim
    0.42
    罄
    0.42
     hầu
    0.42
     aggravating
    0.42
    Activations Density 0.000%

    No Known Activations