© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75707
    Prev
    Next
    INDEX
    Explanations

    attitudes about social issues

    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_31_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
     peripheral
    0.32
     stif
    0.31
     question
    0.30
     lệch
    0.29
    Ử
    0.29
    Peripheral
    0.29
     perif
    0.29
     Question
    0.29
    subMenu
    0.28
     survey
    0.28
    POSITIVE LOGITS
     मानवीय
    0.32
    گیرد
    0.30
    阮
    0.30
    支払い
    0.30
     Orang
    0.30
    協議
    0.29
     GBP
    0.29
     OrderedDict
    0.29
    䨐
    0.29
    termilk
    0.29
    Activations Density 0.002%

    No Known Activations