© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13073
    Prev
    Next
    INDEX
    Explanations

    social and marketing concepts

    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_40_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
     Gothic
    0.84
     gothic
    0.73
     goth
    0.66
    ゴ
    0.46
     gout
    0.45
    othic
    0.44
    াহিত
    0.42
     ܥ
    0.40
    ศิลป
    0.40
    got
    0.40
    POSITIVE LOGITS
     social
    1.10
    social
    1.05
    Social
    1.03
     социа
    1.03
     Social
    0.97
     соціа
    0.96
    SOCIAL
    0.96
     социальных
    0.95
     sociale
    0.94
     SOCIAL
    0.93
    Activations Density 0.069%

    No Known Activations