© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159363
    Prev
    Next
    INDEX
    Explanations

    trapped inside, between, above, 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_2_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
    ي
    1.65
    д
    1.49
    ে
    1.47
    ب
    1.45
    ف
    1.44
    د
    1.43
    та
    1.37
    то
    1.36
    い
    1.36
    ி
    1.34
    POSITIVE LOGITS
     (
    0.98
    ,
    0.82
    ede
    0.82
    ן
    0.82
    ння
    0.80
     "*
    0.79
     didn
    0.77
     an
    0.77
     Exceptional
    0.77
    woods
    0.77
    Activations Density 0.001%

    No Known Activations