© 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. 16286
    Prev
    Next
    INDEX
    Explanations

    lives in apartments

    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
    iggio
    0.40
    ayv
    0.37
     نتع
    0.36
    瑩
    0.36
    পুল
    0.36
    пропетров
    0.36
    \<^
    0.34
    Tweets
    0.34
    ostock
    0.34
    pland
    0.33
    POSITIVE LOGITS
     residents
    1.84
     Residents
    1.80
    Residents
    1.74
    residents
    1.66
     Bewohner
    1.64
     resident
    1.55
    Resident
    1.48
     Resident
    1.45
    居民
    1.45
    住
    1.44
    Activations Density 0.050%

    No Known Activations