© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53260
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     seven
    0.48
    <0xBE>
    0.43
     acht
    0.42
     INCLUDE
    0.41
    八
    0.41
     ocho
    0.41
     sieben
    0.41
     tujuh
    0.40
     هفت
    0.40
     QUESTION
    0.40
    POSITIVE LOGITS
     streets
    0.67
     street
    0.65
    ถนน
    0.59
    streets
    0.59
    street
    0.59
     ulic
    0.57
     улицы
    0.57
    街
    0.57
    straat
    0.56
     ули
    0.55
    Activations Density 0.001%

    No Known Activations