© 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. 2211
    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
    nelle
    2.47
    tte
    2.36
    ameleon
    2.21
    jenigen
    2.17
    ve
    2.14
    виси
    2.11
    schild
    2.08
    𝐧
    2.07
     désir
    2.07
    ্দ
    2.04
    POSITIVE LOGITS
    ৮
    2.11
     avea
    2.03
     Toda
    1.97
     timedelta
    1.94
    inthe
    1.94
    ৯
    1.93
    따
    1.87
     어떤
    1.83
    当然
    1.83
    ⚐
    1.82
    Activations Density 0.270%

    No Known Activations