© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112064
    Prev
    Next
    INDEX
    Explanations

    rangle, bling,riel suffixes

    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_2_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
    ı
    1.36
    ü
    1.31
    いです
    1.26
    。
    1.23
    ри
    1.16
    ↵↵
    1.14
    な
    1.11
    ি
    1.09
    ล
    1.08
    ት
    1.05
    POSITIVE LOGITS
    ف
    1.45
     emphasise
    1.10
    urally
    1.09
     employé
    1.09
     emphasised
    1.09
    tttt
    1.08
     emphas
    1.06
     emphasises
    1.06
     opérations
    1.04
     équipe
    1.03
    Activations Density 0.000%

    No Known Activations