© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108191
    Prev
    Next
    INDEX
    Explanations

    socioeconomic

    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_1_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
    m
    1.94
    b
    1.54
    p
    1.26
    1
    1.22
    B
    1.18
    h
    1.13
    d
    1.09
    k
    1.05
    0
    1.02
    to
    1.01
    POSITIVE LOGITS
     an
    1.38
    я
    1.38
    ة
    1.35
     in
    1.29
    ра
    1.22
    ла
    1.22
    น
    1.20
    ও
    1.16
    لی
    1.15
    在我们
    1.12
    Activations Density 0.001%

    No Known Activations