© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198134
    Prev
    Next
    INDEX
    Explanations

    alter or transform

    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_50_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
    ર
    0.44
    ER
    0.41
    R
    0.41
    ෑ
    0.39
    Barr
    0.38
     savoir
    0.38
    UR
    0.37
    tour
    0.37
    andi
    0.37
    
    0.37
    POSITIVE LOGITS
     lata
    0.44
     altering
    0.43
    ulti
    0.43
     lat
    0.41
    ulta
    0.41
     imgSrc
    0.41
    ult
    0.41
     Mira
    0.40
    ALTER
    0.39
    ucch
    0.39
    Activations Density 0.001%

    No Known Activations