© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130881
    Prev
    Next
    INDEX
    Explanations

    exaggerated or exaggeration

    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_1_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
    น
    1.44
    ش
    1.41
    س
    1.36
    ف
    1.09
    न
    1.05
    ல
    1.01
    ن
    0.99
    ز
    0.96
    માં
    0.96
    ہ
    0.96
    POSITIVE LOGITS
    at
    1.15
    تهم
    0.96
    っている
    0.91
    owy
    0.89
    IK
    0.87
    خیص
    0.85
    because
    0.84
     calving
    0.84
    fromDate
    0.84
    煐
    0.83
    Activations Density 0.001%

    No Known Activations