© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216817
    Prev
    Next
    INDEX
    Explanations

    common, mutual, or unifying concepts

    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
     Africans
    0.42
     Russians
    0.39
     Branches
    0.38
    ewall
    0.36
     AFRICA
    0.35
     Afro
    0.34
    frica
    0.34
    뜯
    0.33
     branches
    0.33
     Nigerians
    0.33
    POSITIVE LOGITS
     gemeinsamen
    0.51
     uniting
    0.48
     zajed
    0.48
     gemeinsame
    0.47
     inter
    0.46
     مشتر
    0.45
    统一
    0.45
    共同
    0.43
    互相
    0.43
     interconnect
    0.42
    Activations Density 0.058%

    No Known Activations