© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192981
    Prev
    Next
    INDEX
    Explanations

    is reflexive

    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_4_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
    ྪ
    0.91
    行う
    0.89
    么
    0.83
    ่า
    0.83
    ৩
    0.82
    ்கு
    0.81
    스
    0.81
    ்ப்ப
    0.80
    ON
    0.79
    வசாய
    0.79
    POSITIVE LOGITS
    ur
    1.63
    il
    1.12
    re
    1.05
    ul
    1.05
    5
    1.03
    y
    1.02
    ا
    0.98
     to
    0.97
    1
    0.96
    a
    0.88
    Activations Density 0.000%

    No Known Activations