© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229724
    Prev
    Next
    INDEX
    Explanations

    dealing with

    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_6_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
    ف
    1.48
    ע
    1.36
    یک
    1.31
    א
    1.20
    ص
    1.15
    ب
    1.12
    אס
    1.04
    ع
    1.04
    או
    1.01
    ي
    1.00
    POSITIVE LOGITS
    :
    1.05
    el
    0.94
     مشترك
    0.87
    cheid
    0.84
    ividade
    0.84
     artist
    0.82
    ka
    0.81
    klasse
    0.81
     concept
    0.80
     adjective
    0.80
    Activations Density 0.001%

    No Known Activations