© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6454
    Prev
    Next
    INDEX
    Explanations

    acoustic oscillation nuclear fusion

    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_40_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
    Gan
    0.46
     salam
    0.44
     star
    0.43
     atenção
    0.43
     Helio
    0.42
     superstar
    0.41
    汽
    0.40
     estrellas
    0.40
    ַ
    0.40
    ӑ
    0.40
    POSITIVE LOGITS
     spectrosc
    0.43
     মেয়র
    0.42
    激活
    0.41
     निर्वा
    0.39
     fiber
    0.37
     exercised
    0.37
     activated
    0.36
     sd
    0.36
    ht
    0.36
    itats
    0.35
    Activations Density 0.026%

    No Known Activations