© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10978
    Prev
    Next
    INDEX
    Explanations

    character setsregex quantifiers

    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
     *
    0.54
     n
    0.47
    D
    0.47
    æ
    0.44
    ê
    0.42
     dresses
    0.42
    ì
    0.41
     presence
    0.40
    Test
    0.40
    able
    0.40
    POSITIVE LOGITS
    ⑵
    0.49
    ４
    0.49
     Вайлд
    0.48
    ７
    0.47
    ओएस
    0.46
    ᅡ
    0.46
     Landkreis
    0.46
    ８
    0.43
    AndKeys
    0.43
    )-$
    0.43
    Activations Density 0.105%

    No Known Activations