© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110168
    Prev
    Next
    INDEX
    Explanations

    for-profit or not-for-profit

    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_2_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
    1.61
    V
    1.50
    J
    1.45
    Y
    1.44
    I
    1.36
    B
    1.35
    K
    1.34
    "
    1.30
    h
    1.30
    :
    1.28
    POSITIVE LOGITS
     importe
    1.34
    т
    1.32
    لية
    1.20
    وں
    1.12
     осуществ
    1.09
    the
    1.06
     использова
    1.06
    الى
    1.02
    ח
    1.01
     actifs
    1.00
    Activations Density 0.000%

    No Known Activations