© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30657
    Prev
    Next
    INDEX
    Explanations

    one or two bedroom

    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
    ശ്ശ
    0.41
    িয়া
    0.36
     entendu
    0.36
     шла
    0.36
    वार्
    0.35
    អ
    0.35
    arding
    0.34
    MsgCallBack
    0.34
    佲
    0.34
    씐
    0.34
    POSITIVE LOGITS
     bedroom
    1.46
     bedrooms
    1.38
     Bedroom
    1.36
    bedroom
    1.35
     Bedrooms
    1.27
    Bedroom
    1.26
    bedrooms
    1.12
    卧室
    1.11
     beds
    0.81
    Rooms
    0.79
    Activations Density 0.003%

    No Known Activations