© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157563
    Prev
    Next
    INDEX
    Explanations

    Ade

    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
    浧
    0.39
     th
    0.39
    enea
    0.38
     delà
    0.38
     Paxton
    0.38
    цен
    0.38
    Б
    0.38
    푐
    0.37
     mana
    0.37
    сня
    0.37
    POSITIVE LOGITS
    urred
    0.41
     Beige
    0.41
    で使用
    0.38
    igl
    0.35
     Zain
    0.35
    mprj
    0.35
     Pelican
    0.35
    τον
    0.35
     स्पॉट
    0.35
    bein
    0.34
    Activations Density 0.000%

    No Known Activations