© 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. 2798
    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
    一是
    0.90
    holder
    0.87
    𝑬
    0.80
    eae
    0.79
     vests
    0.79
     nucleon
    0.78
    COME
    0.78
    یر
    0.77
    za
    0.77
     trivalent
    0.77
    POSITIVE LOGITS
    س
    1.09
     hätten
    0.93
     ня
    0.88
    <0x80>
    0.85
     IBOutlet
    0.85
     bores
    0.85
     begitu
    0.84
    ණ
    0.82
    ์
    0.80
    Woh
    0.80
    Activations Density 0.035%

    No Known Activations