© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17880
    Prev
    Next
    INDEX
    Explanations

    indoor or inside contexts

    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
    ֡
    0.42
     barr
    0.38
    柤
    0.38
     एनी
    0.37
     mathcolor
    0.37
     anot
    0.36
    拦截
    0.36
    یان
    0.35
    bitflag
    0.35
    ㏄
    0.34
    POSITIVE LOGITS
     indoor
    3.14
    Indoor
    2.97
     Indoor
    2.92
    indoor
    2.80
     indoors
    2.72
    室内
    2.50
    屋内
    1.98
     intérieur
    1.36
     Innen
    1.34
     Indo
    1.32
    Activations Density 0.060%

    No Known Activations