© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213206
    Prev
    Next
    INDEX
    Explanations

    youtuber

    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_5_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
    i
    1.68
    "
    1.18
    "。
    1.12
    ↵↵
    1.06
    on
    1.02
    "./
    1.00
    ي
    0.97
    ্ড
    0.96
    "%(
    0.96
    白
    0.96
    POSITIVE LOGITS
    ни
    1.22
     (
    1.15
    м
    1.12
     endereço
    1.09
    ня
    1.01
     одежда
    0.98
     мето
    0.95
     fotografía
    0.95
     tutela
    0.93
    0
    0.93
    Activations Density 0.000%

    No Known Activations