© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141433
    Prev
    Next
    INDEX
    Explanations

    conversational snippets

    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_46_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
    Wel
    0.39
    oraus
    0.38
    ப்பட்டன
    0.37
     पवित्र
    0.36
    oresis
    0.36
    %%%%%%%%%%%%%
    0.36
    ern
    0.35
     প্রাপ্ত
    0.35
    Bluetooth
    0.35
    愤
    0.35
    POSITIVE LOGITS
    illerie
    0.45
     lir
    0.41
    xA
    0.40
    اٹ
    0.39
     Host
    0.38
     AsyncTask
    0.38
     Head
    0.36
     livery
    0.36
    UTION
    0.36
    ailand
    0.36
    Activations Density 0.010%

    No Known Activations