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

    Combinatorics

    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_47_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
    iseerd
    0.43
    ‌های
    0.39
     sels
    0.38
     LN
    0.38
    izieren
    0.38
    ⎜
    0.37
     இந்ந
    0.36
    rotnie
    0.35
    IS
    0.35
     IS
    0.35
    POSITIVE LOGITS
    onyms
    0.41
    ضمن
    0.39
    鈦
    0.37
    ضيف
    0.37
    adde
    0.37
    thereum
    0.36
    দিত
    0.36
    穂
    0.36
     vigor
    0.35
    weiten
    0.35
    Activations Density 0.001%

    No Known Activations