© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167529
    Prev
    Next
    INDEX
    Explanations

    building housing

    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_31_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
    কেশ
    0.36
    蟄
    0.35
     مسلمانوں
    0.34
    ίες
    0.33
     눌
    0.33
    appelijke
    0.32
    icea
    0.32
     மூட
    0.31
    íveis
    0.31
     Workmen
    0.31
    POSITIVE LOGITS
     put
    0.34
    旨
    0.33
     regarded
    0.31
    らしい
    0.31
     sét
    0.31
     FAA
    0.31
    偶
    0.31
     reacted
    0.30
    patterns
    0.30
     Compose
    0.30
    Activations Density 0.001%

    No Known Activations