© 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. 1590
    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
    о
    1.53
     biofilms
    1.26
    nonzero
    1.15
     notions
    1.09
    েল
    1.08
     bottomLeft
    1.08
    countdown
    1.07
    <unused149>
    1.06
     JsonSerializer
    1.05
    
    1.04
    POSITIVE LOGITS
    y
    1.48
    am
    1.32
     već
    1.24
    𝐮
    1.16
    𝐚
    1.16
    िक
    1.15
    ל
    1.14
    𝐲
    1.11
     तरफ
    1.06
    Произ
    1.05
    Activations Density 0.008%

    No Known Activations