© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42857
    Prev
    Next
    INDEX
    Explanations

    code and data structures

    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_13_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
    aikum
    0.49
    ۽
    0.45
    nem
    0.45
    同年
    0.45
     Prag
    0.44
    </h2>
    0.44
     resuming
    0.44
     .”
    0.44
     ,
    0.43
     ).
    0.43
    POSITIVE LOGITS
     flota
    0.54
     স্বর্ণ
    0.49
     bolso
    0.48
    ことなく
    0.48
     blueberries
    0.48
     flu
    0.48
    Flicky
    0.47
     figura
    0.46
     Heron
    0.46
    б
    0.46
    Activations Density 0.000%

    No Known Activations