© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58081
    Prev
    Next
    INDEX
    Explanations

    social responsibility

    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_2_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
    an
    1.52
    า
    1.48
    o
    1.39
    os
    1.34
     a
    1.30
    u
    1.26
    in
    1.23
    1
    1.19
    ia
    1.17
    a
    1.15
    POSITIVE LOGITS
    ت
    1.45
    ಬ್ಬಿಣ
    1.35
    ם
    1.06
     has
    1.04
     legumes
    1.02
    ق
    1.02
     Πε
    1.01
    고
    0.99
     khaki
    0.98
    𝑠
    0.98
    Activations Density 0.001%

    No Known Activations