© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67426
    Prev
    Next
    INDEX
    Explanations

    participants and subjects

    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_41_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
    )]=
    0.42
     rutas
    0.42
     neler
    0.41
    嚷
    0.40
    }^{+}+
    0.40
    モリ
    0.39
     muestras
    0.38
    伡
    0.38
     masa
    0.38
     DCC
    0.37
    POSITIVE LOGITS
     subjects
    0.70
     Subjects
    0.66
    subjects
    0.61
     Ss
    0.60
    Subjects
    0.60
    Subject
    0.59
    Ss
    0.58
     participants
    0.55
     sujetos
    0.55
     SUBJECT
    0.55
    Activations Density 0.001%

    No Known Activations