© 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-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21843
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_56_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
     enseign
    0.37
    탰
    0.34
    မျ
    0.34
    चित
    0.34
    issé
    0.34
     fortale
    0.34
    危
    0.34
    ̷
    0.34
     Championships
    0.33
    წერა
    0.32
    POSITIVE LOGITS
     neo
    0.40
     خب
    0.37
    Neo
    0.36
     vanguard
    0.36
    玄
    0.36
    istan
    0.35
     Neo
    0.35
     sdl
    0.35
     حفظ
    0.34
     neoc
    0.33
    Activations Density 0.009%

    No Known Activations