© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3468
    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
    其他
    2.48
    द
    2.45
    小
    2.17
     ró
    2.10
    อร์
    2.09
     ώστε
    2.05
     nobis
    2.02
    ندہ
    2.02
    geq
    2.00
    服务
    2.00
    POSITIVE LOGITS
    amp
    3.20
    諧
    2.76
    rogens
    2.75
    romeda
    2.61
    quot
    2.59
    того
    2.59
    rews
    2.57
    Amp
    2.44
    mdash
    2.43
    rog
    2.42
    Activations Density 0.011%

    No Known Activations