© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1629
    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
    Not in Any Lists

    No Comments

    Negative Logits
    まあ
    2.76
    ɖ
    2.73
    но
    2.59
    ený
    2.55
     середине
    2.54
    xpath
    2.42
    čné
    2.42
    NAD
    2.37
    fixed
    2.36
     volonté
    2.32
    POSITIVE LOGITS
    з
    2.93
    ل
    2.84
    ங்கிணை
    2.78
     necess
    2.68
    atge
    2.66
    సర
    2.55
    etzten
    2.33
     martingale
    2.33
    ያን
    2.31
     pleasant
    2.30
    Activations Density 0.016%

    No Known Activations