© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7374
    Prev
    Next
    INDEX
    Explanations

    Massachusetts, NY, Maryland

    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_39_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
     León
    0.41
     Deere
    0.40
     неве
    0.38
    圆
    0.38
     туда
    0.37
     салу
    0.35
     हर्षवर्धन
    0.35
    쌈
    0.35
    玧
    0.35
     \%$,
    0.34
    POSITIVE LOGITS
     mary
    0.41
    mary
    0.40
     MARY
    0.39
     treats
    0.38
     Care
    0.37
    ពួក
    0.37
    Helmet
    0.37
    idade
    0.37
    გრ
    0.36
     withdrawal
    0.36
    Activations Density 0.029%

    No Known Activations