© 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. 1077
    Prev
    Next
    INDEX
    Explanations

    voice cloning, remote desktop, user experience, birth chart

    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
    BatchNorm
    0.39
    """.
    0.39
    凳
    0.38
    aima
    0.36
    cognitive
    0.35
    Starts
    0.34
    {{\
    0.34
     新款
    0.34
     smartwatch
    0.34
     cognitive
    0.33
    POSITIVE LOGITS
    າດ
    0.40
     art
    0.38
     NAV
    0.37
     verkl
    0.37
     материалов
    0.35
     wound
    0.34
     дизай
    0.34
    messageInfo
    0.34
    ilecek
    0.33
     envelop
    0.33
    Activations Density 0.133%

    No Known Activations