© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45791
    Prev
    Next
    INDEX
    Explanations

    temperance movement or union

    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_3_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
     on
    0.77
    ３
    0.75
    是因为
    0.74
     ۳
    0.71
    ü
    0.71
    ری
    0.70
    د
    0.70
     bloke
    0.70
     seaborn
    0.68
     ૩
    0.66
    POSITIVE LOGITS
    0
    1.02
    at
    1.02
    the
    0.82
    া
    0.79
    ца
    0.78
    er
    0.77
    lens
    0.76
    yourself
    0.72
    ,
    0.72
    lara
    0.71
    Activations Density 0.002%

    No Known Activations