© 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. 133670
    Prev
    Next
    INDEX
    Explanations

    airy tales, fuzzy matching

    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
     in
    1.09
    的手
    0.89
    كة
    0.88
     في
    0.84
    غ
    0.79
    在
    0.78
    然而
    0.78
    的能力
    0.77
     financier
    0.76
    ták
    0.76
    POSITIVE LOGITS
    a
    1.74
    y
    1.55
    am
    1.54
    ה
    1.52
    ни
    1.41
    at
    1.38
    ע
    1.34
    ic
    1.28
    your
    1.28
    на
    1.27
    Activations Density 0.000%

    No Known Activations