© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1171
    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
    ns
    3.23
    dk
    3.17
    d
    3.13
    tt
    3.13
    nd
    3.08
    tive
    2.95
    렛
    2.94
    dichlor
    2.94
    tiba
    2.90
    cribe
    2.88
    POSITIVE LOGITS
    ু
    2.83
    ב
    2.80
    рих
    2.71
    ل
    2.64
    ర
    2.54
    ान
    2.51
    ak
    2.45
     sequ
    2.43
    নাথ
    2.42
    𝕡
    2.42
    Activations Density 0.821%

    No Known Activations