© 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. 9205
    Prev
    Next
    INDEX
    Explanations

    algunos ejemplos

    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
    EqualTo
    2.62
    стики
    2.59
    ʟ
    2.56
    िक
    2.47
    ू
    2.46
    п
    2.40
    า
    2.37
    лены
    2.32
    𝐫
    2.29
    டியான
    2.27
    POSITIVE LOGITS
     macam
    3.25
    程度上
    2.74
    le
    2.71
     extent
    2.63
    udades
    2.57
    jail
    2.56
    tin
    2.56
     ℝ
    2.51
     nonzero
    2.48
    ties
    2.48
    Activations Density 0.027%

    No Known Activations