© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 98736
    Prev
    Next
    INDEX
    Explanations

    stand out, differentiate from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_16_width_262k_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
     t
    0.28
     insufficiency
    0.27
     southernmost
    0.27
     robber
    0.27
    каза
    0.26
    פת
    0.26
    чками
    0.26
     transformations
    0.26
     testes
    0.26
     robbers
    0.25
    POSITIVE LOGITS
     Hermitian
    0.31
     \{
    0.31
    °;
    0.29
     $\{$
    0.29
     Asher
    0.29
     Coker
    0.28
    тли
    0.28
     $\{
    0.27
     відео
    0.27
     Copeland
    0.27
    Activations Density 0.085%

    No Known Activations