© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196975
    Prev
    Next
    INDEX
    Explanations

    likely due to, not due to

    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_27_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
     junit
    0.40
     glamour
    0.40
     Agree
    0.37
     Ababa
    0.37
    тисти
    0.36
     chmod
    0.36
    huge
    0.36
    所
    0.36
     mocks
    0.35
    بيقات
    0.35
    POSITIVE LOGITS
     vols
    0.44
     printed
    0.38
     बेरोजगार
    0.38
     livelihood
    0.37
    সক
    0.37
    zny
    0.36
     किन
    0.36
     apologies
    0.36
     solvency
    0.35
    
    0.34
    Activations Density 0.000%

    No Known Activations