© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15440
    Prev
    Next
    INDEX
    Explanations

    cabinets and drawers

    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_34_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
    炎
    0.38
    殞
    0.38
     Instrumentation
    0.37
     Concentration
    0.36
     Urinary
    0.36
    刺
    0.36
    Rotating
    0.36
     elaborate
    0.35
     instrumentation
    0.35
    滂
    0.35
    POSITIVE LOGITS
     cabinets
    0.84
     cabinet
    0.83
     CABINET
    0.81
     Cabinet
    0.81
     cabinetry
    0.81
    Cabinet
    0.78
     कैबिनेट
    0.77
    cabinet
    0.77
    櫥
    0.75
     шка
    0.73
    Activations Density 0.016%

    No Known Activations