© 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. 9160
    Prev
    Next
    INDEX
    Explanations

    location, spot, ending

    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
     तौर
    1.39
    volving
    1.02
    orchid
    1.01
    zna
    0.98
    holds
    0.97
    lijke
    0.96
    hhh
    0.95
     있게
    0.95
    н
    0.95
    hhhh
    0.94
    POSITIVE LOGITS
     Tuttavia
    1.12
     contrô
    1.10
     Kalian
    1.06
     vienen
    1.06
    する
    1.04
     wszyst
    1.01
    г
    1.01
     factoring
    1.00
     spéciales
    1.00
    en
    0.99
    Activations Density 0.006%

    No Known Activations