© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92170
    Prev
    Next
    INDEX
    Explanations

    results in

    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_11_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
     बाथरूम
    0.48
    एम
    0.48
    Vars
    0.46
    C
    0.46
    M
    0.44
     clapping
    0.44
    Tera
    0.43
    Gay
    0.43
     sosyal
    0.43
    देश
    0.43
    POSITIVE LOGITS
    ě
    0.49
     >,
    0.45
     I
    0.44
     incision
    0.42
     >
    0.39
     rupani
    0.38
    >.
    0.37
    ů
    0.37
     cannibal
    0.37
     umožňuje
    0.36
    Activations Density 0.002%

    No Known Activations