© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31488
    Prev
    Next
    INDEX
    Explanations

    bicameral, bic, houses

    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
    .³
    0.41
     ২০
    0.39
     treinta
    0.38
     Thirty
    0.38
    èlement
    0.38
    Thirty
    0.38
    ៕
    0.38
    ℧
    0.37
     grouping
    0.36
     thirty
    0.36
    POSITIVE LOGITS
     bic
    1.04
     Bic
    0.83
    bic
    0.72
     tric
    0.72
     bik
    0.67
     BIC
    0.63
    bik
    0.61
     Bik
    0.60
     biker
    0.60
     bikers
    0.59
    Activations Density 0.038%

    No Known Activations