© 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. 50353
    Prev
    Next
    INDEX
    Explanations

    danke, Döner, Darm, Dampf

    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
     connect
    0.40
     navig
    0.39
     adapt
    0.38
     দিয়েছেন
    0.38
     indicators
    0.38
     pro
    0.38
     cadastro
    0.38
    佲
    0.38
     અસર
    0.37
     Images
    0.37
    POSITIVE LOGITS
     التجارية
    0.41
    ropo
    0.37
    ↩
    0.37
    ற்போது
    0.36
    return
    0.36
    бами
    0.35
    につき
    0.34
    र्देश
    0.34
    வர்களை
    0.34
    overs
    0.34
    Activations Density 0.003%

    No Known Activations