© 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. 708
    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
    ূট
    0.25
    watches
    0.24
    sanitize
    0.23
    lera
    0.23
     परेशान
    0.22
     इससे
    0.22
    tableName
    0.22
    䥑
    0.22
    persons
    0.21
    Мушко
    0.21
    POSITIVE LOGITS
    י
    0.29
    re
    0.26
    й
    0.24
    которы
    0.23
    en
    0.22
    ../../
    0.21
    عل
    0.21
    el
    0.21
    ో
    0.21
    ره
    0.20
    Activations Density 0.165%

    No Known Activations