© 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. 9191
    Prev
    Next
    INDEX
    Explanations

    eye to eye

    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
    \,\
    3.11
     behold
    2.82
     xét
    2.81
     сами
    2.74
     👀
    2.72
     hatches
    2.68
     Xét
    2.65
     fruitless
    2.62
    }></
    2.62
     Alessandra
    2.58
    POSITIVE LOGITS
    pang
    2.44
    faced
    2.43
     kez
    2.41
    دت
    2.34
    ز
    2.32
    ো
    2.30
    wig
    2.25
     нема
    2.24
    ži
    2.22
    신도시
    2.21
    Activations Density 0.009%

    No Known Activations