© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120637
    Prev
    Next
    INDEX
    Explanations

    arrival/departure times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
     propuesta
    0.37
    ilecek
    0.37
     proposta
    0.35
     nap
    0.35
    utama
    0.35
    ū
    0.35
    GMP
    0.35
    čk
    0.34
    ctic
    0.34
    してみました
    0.34
    POSITIVE LOGITS
     अभ
    0.39
     丿
    0.37
    ประสิทธิภาพ
    0.37
    གྲ
    0.37
     شرق
    0.36
    ்துற
    0.35
     தொடர்பு
    0.35
    VERSE
    0.34
    incredible
    0.34
     सिले
    0.34
    Activations Density 0.022%

    No Known Activations