© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 213238
    Prev
    Next
    INDEX
    Explanations

    ISO

    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_43_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
     Alma
    0.39
    Lai
    0.39
     مر
    0.37
     Hello
    0.37
     Chief
    0.36
     trem
    0.36
    ()/
    0.36
    N
    0.36
     зада
    0.35
    AO
    0.35
    POSITIVE LOGITS
    раздо
    0.38
    чать
    0.38
    аны
    0.37
    ባል
    0.37
     साजिश
    0.37
     رجل
    0.37
    бири
    0.37
    ື່ອ
    0.36
    顾问
    0.36
     inkább
    0.36
    Activations Density 0.001%

    No Known Activations