© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139899
    Prev
    Next
    INDEX
    Explanations

    slowing, slow

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     descended
    0.52
     быстро
    0.45
     descends
    0.43
     lapses
    0.43
     descend
    0.41
     rápidos
    0.41
    慢
    0.41
     descending
    0.41
     rapides
    0.41
     rápid
    0.39
    POSITIVE LOGITS
    ->$
    0.44
     الاق
    0.39
    oraus
    0.37
    たない
    0.37
     gew
    0.36
     Avner
    0.36
     sparsity
    0.36
     substituent
    0.35
    রুদ্ধ
    0.35
    guh
    0.35
    Activations Density 0.003%

    No Known Activations