© 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. 3177
    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
    ম্বা
    1.15
    ings
    1.10
    ым
    1.09
    搀
    1.09
    ТЕ
    1.07
     する
    1.06
    কেমিক্যাল
    1.04
    haw
    1.04
    jų
    1.04
    ▲
    1.03
    POSITIVE LOGITS
    or
    1.20
    at
    1.17
    я
    1.13
    ین
    1.12
    ively
    1.10
    el
    1.06
    atement
    1.05
    nahme
    1.05
     \%,
    1.04
    boden
    1.04
    Activations Density 0.224%

    No Known Activations