© 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. 9181
    Prev
    Next
    INDEX
    Explanations

    assignment of variables

    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
    Negative Logits
    y
    3.66
    ᅠ
    3.13
     lampu
    2.92
    Nä
    2.90
    да
    2.84
    টর
    2.78
    ្នែក
    2.74
    𝑒
    2.73
     যাইহোক
    2.73
     plaint
    2.70
    POSITIVE LOGITS
    ================
    5.66
    /=
    4.84
    ============
    4.60
    ===============
    4.44
    ===========
    4.23
    ͟
    3.69
    ==============]
    3.50
    ,=
    3.45
    snp
    2.87
    ⇒
    2.84
    Activations Density 0.172%

    No Known Activations