© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51379
    Prev
    Next
    INDEX
    Explanations

    restaurant descriptions

    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_31_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
     करवाने
    0.35
    ［
    0.34
     connaissez
    0.34
     indefinitely
    0.32
    agnetic
    0.32
    突
    0.32
    éfono
    0.32
    wdriver
    0.32
    ethers
    0.31
    ด้อ
    0.31
    POSITIVE LOGITS
    \}$,
    0.38
    Facilities
    0.36
    signed
    0.34
     подписа
    0.33
    ऐसे
    0.32
     ವಿಶ
    0.32
     Spinal
    0.32
    namespaces
    0.32
     எழுத்த
    0.32
    Alz
    0.31
    Activations Density 0.002%

    No Known Activations