© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 256225
    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_10_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
    डक्शन
    1.23
    లోకి
    1.19
    नेटरी
    1.18
     orifices
    1.18
     regione
    1.17
     Jahrhund
    1.13
    ់
    1.13
     gamme
    1.12
     épisode
    1.10
     nucleons
    1.09
    POSITIVE LOGITS
    t
    1.41
    pet
    1.23
    m
    1.23
    別に
    1.19
    Wis
    1.19
    tım
    1.16
    peter
    1.12
    ੱਚ
    1.12
    prompt
    1.10
    র্শ
    1.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.