© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155256
    Prev
    Next
    INDEX
    Explanations

    say common word endings

    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
     keempat
    0.51
     నాలుగు
    0.50
     cuatro
    0.50
    Four
    0.49
     dört
    0.49
    四个
    0.48
    四
    0.48
     चार
    0.47
    <0xBE>
    0.47
     quatro
    0.46
    POSITIVE LOGITS
     demanda
    0.41
     preceding
    0.38
     Vu
    0.38
     engraved
    0.38
    ្ឋ
    0.37
     TimeSpan
    0.37
    ceso
    0.36
     cocker
    0.36
    उचर
    0.35
     ஆலய
    0.35
    Activations Density 0.014%

    No Known Activations