© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10351
    Prev
    Next
    INDEX
    Explanations

    withstand scrutiny / take it / endure

    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_13_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
    ov
    0.49
     différen
    0.48
    (/(
    0.47
     ছিলনা
    0.46
     ponctu
    0.45
    า
    0.45
     oder
    0.43
    mAvailable
    0.43
    hos
    0.43
    ätzlich
    0.43
    POSITIVE LOGITS
     cathodic
    0.46
     Talmud
    0.43
    larla
    0.42
     sublime
    0.41
     향
    0.41
     நூற்ற
    0.40
     ক্যাথ
    0.40
    retto
    0.40
     camino
    0.39
    layered
    0.39
    Activations Density 0.007%

    No Known Activations