© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 210167
    Prev
    Next
    INDEX
    Explanations

    weld, glue, seams, connect, rust

    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_19_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
     harmless
    0.15
    قبل
    0.15
    Ꮒ
    0.15
    enu
    0.14
    eno
    0.14
     s
    0.14
     prieš
    0.13
    較
    0.13
     sab
    0.13
    ignons
    0.13
    POSITIVE LOGITS
    produto
    0.16
     profesionales
    0.16
     kuliah
    0.15
    TRADE
    0.15
     pietra
    0.15
     TRADE
    0.15
     tokamaks
    0.15
    পোর্ট
    0.14
     strumenti
    0.14
    Produto
    0.14
    Activations Density 0.003%

    No Known Activations