© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90733
    Prev
    Next
    INDEX
    Explanations

    compartments

    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_60_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
     compartments
    2.69
     compartment
    2.67
     compartmental
    2.66
     Compart
    2.55
    Compart
    2.44
    compart
    2.42
     compart
    2.30
    厢
    0.65
     compartido
    0.64
    舱
    0.61
    POSITIVE LOGITS
     COMP
    0.61
    COMP
    0.48
     com
    0.38
     комиссии
    0.36
     kom
    0.35
    コン
    0.34
     구
    0.34
    ებ
    0.33
     council
    0.33
     če
    0.33
    Activations Density 0.008%

    No Known Activations