© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 4197
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    д
    2.10
     minded
    1.91
    Salut
    1.90
    ದ್ದ
    1.68
     הה
    1.66
     jist
    1.65
    המ
    1.65
    ه
    1.64
    ायतों
    1.63
    }$
    1.62
    POSITIVE LOGITS
    tions
    2.42
     respectivas
    2.23
    ashore
    1.98
     amorphous
    1.94
    tgt
    1.91
    வற்றை
    1.91
    በት
    1.90
    tion
    1.85
    tic
    1.83
     أعمال
    1.82
    Activations Density 0.184%

    No Known Activations