© 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. 54012
    Prev
    Next
    INDEX
    Explanations

    welfare, TANF, social services

    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
     Twenty
    0.40
     Ninety
    0.40
    碎片
    0.40
    댐
    0.38
     Eighty
    0.37
     reserv
    0.36
     Fifty
    0.36
     ২১
    0.36
    圈
    0.36
     Bartholom
    0.35
    POSITIVE LOGITS
     TAN
    0.41
    evil
    0.40
    stereo
    0.38
    হান
    0.38
     evil
    0.38
     YANG
    0.37
    onuclear
    0.37
     nõ
    0.36
     تمت
    0.36
     stereo
    0.36
    Activations Density 0.028%

    No Known Activations