© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9295
    Prev
    Next
    INDEX
    Explanations

    health and human services programs

    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_13_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
     Ols
    0.48
     northward
    0.48
     soggy
    0.47
     informações
    0.45
     north
    0.44
     cidade
    0.44
     n
    0.43
     arbet
    0.43
     città
    0.43
     ნ
    0.43
    POSITIVE LOGITS
    colare
    0.43
    разу
    0.42
    orpion
    0.42
    inerary
    0.42
     médicos
    0.41
    жден
    0.41
    medical
    0.41
    مرين
    0.41
    Comedy
    0.40
    scalars
    0.40
    Activations Density 0.012%

    No Known Activations