© 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. 9068
    Prev
    Next
    INDEX
    Explanations

    sys.version, rc.local, Sakura

    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
     conjunction
    2.75
    ी
    2.69
    ي
    2.67
    л
    2.64
    mittel
    2.53
    どこ
    2.50
    नाथ
    2.47
     العافيه
    2.43
     kterou
    2.40
    ाब
    2.38
    POSITIVE LOGITS
    impurity
    2.49
    employment
    2.38
    
    2.36
    
    2.31
    rying
    2.26
     recombination
    2.24
     MonoBehaviour
    2.21
     åter
    2.20
    immersive
    2.19
     hysteresis
    2.10
    Activations Density 0.000%

    No Known Activations