© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63324
    Prev
    Next
    INDEX
    Explanations

    Poznań/Russian greetings

    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_46_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
     highlight
    0.46
     Highlight
    0.42
     судо
    0.41
     highlights
    0.41
    姿
    0.40
     lực
    0.38
     ราศี
    0.38
     highland
    0.38
     core
    0.38
    ọt
    0.37
    POSITIVE LOGITS
    abo
    0.38
    amaan
    0.38
    БО
    0.38
    haa
    0.37
    =@
    0.36
    achan
    0.35
    ன்னு
    0.35
    enna
    0.34
    ពិសេស
    0.34
    APAN
    0.34
    Activations Density 0.000%

    No Known Activations