© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5677
    Prev
    Next
    INDEX
    Explanations

    programming code syntax

    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_44_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
    <unused197>
    0.21
     रिलेट
    0.21
    ريف
    0.20
     ግራም
    0.20
    <unused1894>
    0.20
     размера
    0.19
     пенсии
    0.19
     boilers
    0.19
     whanne
    0.19
     omkring
    0.19
    POSITIVE LOGITS
    led
    0.19
     International
    0.18
     Ra
    0.18
     P
    0.18
     Am
    0.17
    ders
    0.17
     So
    0.17
    Ra
    0.17
     All
    0.17
     Be
    0.17
    Activations Density 0.060%

    No Known Activations