© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50930
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Int
    0.43
     Goes
    0.41
     פי
    0.40
     تساعد
    0.40
     Recurring
    0.40
     gespre
    0.38
    ֻ
    0.38
    goes
    0.37
    豐富
    0.37
    敺
    0.37
    POSITIVE LOGITS
    aji
    0.43
     bag
    0.40
    anyard
    0.40
    achery
    0.38
     alum
    0.38
    aja
    0.36
     الحال
    0.36
    bag
    0.36
    Есть
    0.36
     вероятно
    0.35
    Activations Density 0.000%

    No Known Activations