© 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. 3687
    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
    ção
    2.61
    ка
    2.51
    ঈদ
    2.26
    %%%%%%%%%%%%%%%%
    2.24
    ৯
    2.23
    elijkheid
    2.22
    %%%%%%%%
    2.19
    paused
    2.18
    يك
    2.16
    ̫
    2.15
    POSITIVE LOGITS
    TIA
    2.52
    р
    2.51
     teasing
    2.37
    𝒑
    2.36
     noses
    2.34
    𝒄
    2.33
    𝒅
    2.26
    اف
    2.25
     fend
    2.22
     encompass
    2.22
    Activations Density 0.034%

    No Known Activations