© 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. 1980
    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
     consigo
    2.88
    in
    2.57
     oración
    2.57
    er
    2.55
    л
    2.48
     concerted
    2.40
    lj
    2.40
     amely
    2.40
    з
    2.38
     uiteindelijk
    2.33
    POSITIVE LOGITS
    𝒂
    2.70
    𝒖
    2.69
    ע
    2.50
    𝒃
    2.48
     denominator
    2.46
    timeLeft
    2.44
    cemic
    2.42
    𝒓
    2.41
     HomePage
    2.40
    AppBsky
    2.38
    Activations Density 0.064%

    No Known Activations