© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200668
    Prev
    Next
    INDEX
    Explanations

    robot locomotion

    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_12_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
    
    0.52
     roto
    0.48
     accuse
    0.48
     jell
    0.48
     Xinhua
    0.48
    ☀
    0.47
     limo
    0.47
     홈
    0.46
     absorb
    0.46
     ይሰ
    0.46
    POSITIVE LOGITS
    of
    0.58
    реа
    0.51
    ה
    0.48
    What
    0.47
    quoi
    0.47
    ُّ
    0.47
    ти
    0.46
    ря
    0.46
    قم
    0.45
    энд
    0.45
    Activations Density 0.002%

    No Known Activations