© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138212
    Prev
    Next
    INDEX
    Explanations

    Arabic diacritics and suffixes

    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_12_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
    la
    0.54
     exuber
    0.54
    '
    0.54
     я
    0.52
    ätter
    0.52
     overwhelmed
    0.50
     enjoying
    0.50
     affording
    0.50
     because
    0.49
    igning
    0.49
    POSITIVE LOGITS
    X
    0.53
    Delete
    0.52
     nulla
    0.51
    StateToProps
    0.50
    amse
    0.49
     ioe
    0.49
    Lane
    0.49
    }(\
    0.47
     addNew
    0.47
    Holmes
    0.47
    Activations Density 0.000%

    No Known Activations