© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13722
    Prev
    Next
    INDEX
    Explanations

    Lis, Liz, Lisa, Liszt, Lisp

    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_40_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
    mittel
    0.41
     countably
    0.38
     विरासत
    0.37
    arik
    0.37
    duk
    0.36
     കാരണ
    0.35
    getRuntime
    0.35
    湁
    0.34
     Dakar
    0.34
    ಧಾರ
    0.34
    POSITIVE LOGITS
     अभि
    0.45
    negie
    0.40
     घु
    0.37
     બે
    0.36
     eyebrow
    0.36
    बहन
    0.36
     刘
    0.36
     வெளிய
    0.35
     Salam
    0.35
    Lisa
    0.35
    Activations Density 0.010%

    No Known Activations