© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 262055
    Prev
    Next
    INDEX
    Explanations

    Tags:

    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_22_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
     ferrous
    0.43
    ravo
    0.41
    WQ
    0.39
     reality
    0.39
    禣
    0.38
     coal
    0.38
     becomes
    0.37
     seen
    0.37
    seen
    0.37
    انیہ
    0.37
    POSITIVE LOGITS
     możliwość
    0.43
    odesmium
    0.42
     Size
    0.39
    myItemType
    0.39
    纽约
    0.38
     الاقوامی
    0.38
    юй
    0.37
    Cambridge
    0.37
    覓
    0.37
    ócio
    0.37
    Activations Density 0.000%

    No Known Activations