© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37504
    Prev
    Next
    INDEX
    Explanations

    your + noun

    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_3_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
    א
    1.25
    ان
    1.12
    אנ
    1.03
    ।
    1.01
    s
    0.98
    ל
    0.97
    ש
    0.94
    も
    0.86
    。
    0.85
    או
    0.83
    POSITIVE LOGITS
    '
    0.90
     és
    0.76
    that
    0.68
    okban
    0.62
    शिक
    0.57
    ная
    0.57
    行的
    0.57
     خرج
    0.56
     thisobject
    0.55
     irrég
    0.55
    Activations Density 0.014%

    No Known Activations