© 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. 219109
    Prev
    Next
    INDEX
    Explanations

    combining or concatenating elements

    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
     కార్
    0.31
     KSI
    0.30
     முறையாக
    0.30
    मिली
    0.29
     Persons
    0.29
    Accordingly
    0.29
     ____
    0.28
     الكريم
    0.28
    Photograph
    0.28
    ଧ
    0.28
    POSITIVE LOGITS
     né
    0.30
     Gear
    0.30
     Né
    0.29
     Vet
    0.29
     Pá
    0.29
     depende
    0.28
    equalToSuperview
    0.28
     sowie
    0.28
     Sriniv
    0.28
    忍者
    0.28
    Activations Density 0.000%

    No Known Activations