© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5347
    Prev
    Next
    INDEX
    Explanations

    intellectual property rights

    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
    ചന
    0.41
     Resilience
    0.39
    ács
    0.39
    ]#
    0.37
    mL
    0.37
    oil
    0.37
    ﻀ
    0.37
    円
    0.36
     ස්ථා
    0.35
    OIL
    0.34
    POSITIVE LOGITS
     property
    0.86
     propiedad
    0.71
     propriedade
    0.70
    property
    0.68
     propriété
    0.61
     PROPERTY
    0.60
     Property
    0.59
     real
    0.59
     সম্পত্তি
    0.57
     proprietà
    0.56
    Activations Density 0.069%

    No Known Activations