© 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. 33935
    Prev
    Next
    INDEX
    Explanations

    suitcase and baggage

    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
     brakes
    0.40
    驶
    0.39
    ../../../
    0.38
    Crew
    0.38
    槳
    0.38
    停車
    0.37
    (../
    0.36
    停车场
    0.36
    Disc
    0.35
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.35
    POSITIVE LOGITS
    दर
    0.38
    衣
    0.36
     cheaper
    0.36
     Seab
    0.34
     Grey
    0.33
     Barrett
    0.32
     azure
    0.32
    Gee
    0.32
    ໃຊ
    0.32
    ínu
    0.32
    Activations Density 0.011%

    No Known Activations