© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 166599
    Prev
    Next
    INDEX
    Explanations

    Spanish/Portuguese suffixes

    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_56_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
     e
    0.42
     эл
    0.40
     esim
    0.39
     elu
    0.38
     Sim
    0.38
     mukaan
    0.38
    eo
    0.37
     corps
    0.36
    𝓮
    0.36
    टील
    0.36
    POSITIVE LOGITS
    non
    0.47
     unha
    0.44
    unos
    0.43
    ânt
    0.42
     non
    0.41
    nos
    0.40
     uns
    0.40
     tone
    0.39
     غير
    0.39
    SETUP
    0.38
    Activations Density 0.000%

    No Known Activations