© 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. 9176
    Prev
    Next
    INDEX
    Explanations

    TensorFlow

    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
    "",
    2.89
    $_
    2.71
    ύ
    2.68
     ショルダー
    2.63
    }={
    2.60
    но
    2.49
    اء
    2.46
    रु
    2.43
    ној
    2.42
    ʏ
    2.42
    POSITIVE LOGITS
    nél
    2.65
    ش
    2.60
    亼
    2.59
     manner
    2.57
     hoofd
    2.55
    س
    2.52
    ように
    2.48
     percentile
    2.43
    cloth
    2.41
    挞
    2.37
    Activations Density 0.033%

    No Known Activations