© 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. 2055
    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
    or
    0.62
    k
    0.60
    zelfde
    0.53
    कहां
    0.53
    ers
    0.51
    و
    0.49
    at
    0.48
    র
    0.48
    ர்
    0.47
    ডস
    0.47
    POSITIVE LOGITS
    𝐢
    0.60
    𝐞
    0.59
    tı
    0.57
    eing
    0.56
    𝐝
    0.56
    𝐧
    0.54
     dites
    0.54
     Surrounded
    0.51
    sin
    0.50
     ales
    0.50
    Activations Density 0.227%

    No Known Activations