© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154984
    Prev
    Next
    INDEX
    Explanations

    German words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     worldRank
    0.48
     کا
    0.48
     فی
    0.48
     کور
    0.46
    ーフ
    0.46
     دنیا
    0.46
     お
    0.45
     ބ
    0.45
     زید
    0.45
     وک
    0.45
    POSITIVE LOGITS
     dire
    0.78
     Dire
    0.68
    Dire
    0.68
    dire
    0.64
    son
    0.56
     DIRE
    0.54
    Son
    0.53
     son
    0.52
     I
    0.52
     her
    0.50
    Activations Density 0.000%

    No Known Activations