© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4845
    Prev
    Next
    INDEX
    Explanations

    displays . flex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    𝗻
    2.27
    ഹ്ലാദ
    2.27
     éd
    2.21
    en
    2.20
    \},
    2.18
    𝗗
    2.16
    le
    2.15
    ाना
    2.11
    unan
    2.10
    ック
    2.09
    POSITIVE LOGITS
    𝐔
    2.75
    re
    2.64
     licz
    2.63
    ortion
    2.63
    sects
    2.62
     bulge
    2.61
    то
    2.51
     disdain
    2.47
    displays
    2.46
     불구하고
    2.45
    Activations Density 0.063%

    No Known Activations