© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82765
    Prev
    Next
    INDEX
    Explanations

    names and abbreviations

    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_53_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
    দ্দ
    0.44
    Dew
    0.40
    姥
    0.38
     டை
    0.38
     다
    0.38
     Hö
    0.38
    draggable
    0.38
     Mü
    0.37
    োপা
    0.37
    沅
    0.37
    POSITIVE LOGITS
     flash
    0.42
     stil
    0.38
    حم
    0.38
    បង្ហ
    0.37
    ন্ব
    0.37
    weiter
    0.36
     blindness
    0.36
    षी
    0.36
    нтип
    0.35
    ضل
    0.35
    Activations Density 0.002%

    No Known Activations