© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43031
    Prev
    Next
    INDEX
    Explanations

    [::-1] slicing

    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_22_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
    ΤΑ
    0.42
    鎳
    0.42
    ﻦ
    0.41
     imun
    0.40
    cuando
    0.40
    फिल
    0.39
     antioxid
    0.39
    ﺐ
    0.39
    .}$
    0.39
    ренности
    0.39
    POSITIVE LOGITS
     Without
    0.51
     without
    0.48
     zonder
    0.47
    Without
    0.46
     WITHOUT
    0.44
     без
    0.44
     ohne
    0.43
     Rue
    0.42
     Excluding
    0.41
    without
    0.40
    Activations Density 0.002%

    No Known Activations