© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51165
    Prev
    Next
    INDEX
    Explanations

    documentation links

    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_31_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
     utilising
    0.38
    ्वान
    0.37
    ably
    0.36
    旗
    0.36
    Dijstra
    0.35
    ब्दी
    0.35
    slate
    0.35
     понятие
    0.35
    kale
    0.34
    Thai
    0.34
    POSITIVE LOGITS
    لیف
    0.38
     regol
    0.38
    setKeep
    0.37
    纽
    0.37
     Cow
    0.36
     volume
    0.36
     sứ
    0.36
     Cruise
    0.36
    బా
    0.35
     Preheat
    0.35
    Activations Density 0.000%

    No Known Activations