© 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. 9085
    Prev
    Next
    INDEX
    Explanations

    always been

    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
    स
    1.56
    ن
    1.51
    ের
    1.43
    ড
    1.23
     nei
    1.17
    ट
    1.16
     isEqual
    1.16
    sigh
    1.15
     maxWidth
    1.15
    س
    1.13
    POSITIVE LOGITS
     dogged
    1.09
    leşt
    1.05
    oğlu
    1.04
    ரில்
    1.03
    ധ്യമ
    1.03
    esque
    1.02
    neq
    1.02
    batim
    1.01
    pel
    0.99
     наме
    0.95
    Activations Density 0.018%

    No Known Activations