© 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. 196069
    Prev
    Next
    INDEX
    Explanations

    code and hardware

    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
    שו
    0.38
    sens
    0.37
     ಬಹ
    0.36
    ₸
    0.35
    icel
    0.34
     싶은
    0.34
    rim
    0.34
     yar
    0.34
    erent
    0.34
    jet
    0.33
    POSITIVE LOGITS
    ভূত
    0.36
    õi
    0.35
     गुड
    0.35
    ＋
    0.34
    ুনিক
    0.33
    льность
    0.32
    δυ
    0.32
     intArray
    0.32
     разби
    0.32
    Ｌ
    0.32
    Activations Density 0.008%

    No Known Activations