© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2540
    Prev
    Next
    INDEX
    Explanations

    diagnostic trouble codes

    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_40_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
    liko
    0.44
     bebas
    0.41
    磨
    0.41
     voice
    0.38
     voz
    0.38
    pekte
    0.37
     탱
    0.37
     WP
    0.36
     Pacífico
    0.36
     voix
    0.35
    POSITIVE LOGITS
     CAN
    0.39
    Да
    0.38
     दशहरा
    0.38
    CAN
    0.37
     catalyzed
    0.36
     যাবত
    0.36
    Do
    0.36
    rakech
    0.36
    দিনই
    0.35
    Functions
    0.35
    Activations Density 0.044%

    No Known Activations