© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198453
    Prev
    Next
    INDEX
    Explanations

    Example 1:

    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
     よ
    0.39
     काम
    0.36
    ()}')
    0.36
     कार्य
    0.35
    ngthen
    0.35
     prev
    0.35
    ayvachi
    0.34
     পুষ
    0.34
    ៉
    0.34
     অনুষ্ঠ
    0.33
    POSITIVE LOGITS
     futures
    0.42
     mellan
    0.41
    Future
    0.40
     BETWEEN
    0.40
     between
    0.39
    between
    0.38
     Between
    0.38
     emulsion
    0.38
     zwischen
    0.38
     goblet
    0.38
    Activations Density 0.000%

    No Known Activations