© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200049
    Prev
    Next
    INDEX
    Explanations

    room

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ອາ
    0.46
     Vas
    0.42
     vas
    0.40
    秵
    0.38
    आ
    0.38
     չ
    0.37
     Vasily
    0.37
    อา
    0.37
    वास
    0.36
     Василий
    0.36
    POSITIVE LOGITS
     room
    2.11
     Room
    1.93
    Room
    1.91
    room
    1.87
     ROOM
    1.73
    ROOM
    1.55
     комна
    1.36
     रूम
    1.28
    室
    1.20
     कमरे
    1.20
    Activations Density 0.003%

    No Known Activations