© 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. 32051
    Prev
    Next
    INDEX
    Explanations

    social groups and behaviors

    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
    ัป
    0.41
     administer
    0.38
    嗶
    0.37
    ieno
    0.37
     ഉയ
    0.36
     administering
    0.36
    മ്മി
    0.35
    ያን
    0.35
    "./
    0.35
     Moth
    0.35
    POSITIVE LOGITS
     group
    1.38
     groups
    1.30
    group
    1.27
    Group
    1.26
     Groups
    1.26
     Group
    1.25
    グループ
    1.20
     группа
    1.20
     গ্রুপ
    1.18
    groups
    1.17
    Activations Density 0.070%

    No Known Activations