© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216070
    Prev
    Next
    INDEX
    Explanations

    imag

    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_50_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
     U
    0.41
    issor
    0.40
    δέ
    0.39
    Ꮞ
    0.39
     dreary
    0.38
     MRC
    0.38
     HUT
    0.38
     lö
    0.38
     UCC
    0.37
     UD
    0.37
    POSITIVE LOGITS
     प्रोफ
    0.42
     সত
    0.38
    펨
    0.37
     જગ
    0.36
    ipated
    0.36
    covery
    0.35
     전
    0.34
     wound
    0.34
     slag
    0.34
     महावीर
    0.34
    Activations Density 0.000%

    No Known Activations