© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8912
    Prev
    Next
    INDEX
    Explanations

    Ancients

    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
    ⓡ,
    2.58
    th
    2.35
    എ
    2.31
    민국
    2.30
    ına
    2.24
     наблюдения
    2.24
    SendCommand
    2.22
     निजात
    2.21
    =-\
    2.20
    éri
    2.15
    POSITIVE LOGITS
    scrape
    3.00
    𝑒
    2.90
     ومرحبا
    2.68
    কারণ
    2.60
    enn
    2.59
    COMP
    2.56
    وين
    2.55
    anguages
    2.55
    𝒶
    2.54
    𝑜
    2.53
    Activations Density 0.000%

    No Known Activations