© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51685
    Prev
    Next
    INDEX
    Explanations

    loss and amputation

    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_30_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
     regress
    0.34
    க்கொள்ள
    0.34
     сх
    0.34
     Each
    0.33
    twilio
    0.33
    vn
    0.32
    (()=>{
    0.32
    avail
    0.32
     stored
    0.32
    ály
    0.32
    POSITIVE LOGITS
    बो
    0.42
     materiali
    0.40
     последствия
    0.39
    橦
    0.39
     документи
    0.39
     richieste
    0.39
     bastion
    0.39
     vozila
    0.38
    اديه
    0.38
     автомобі
    0.38
    Activations Density 0.000%

    No Known Activations