© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43059
    Prev
    Next
    INDEX
    Explanations

    two main

    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
     misalnya
    0.42
    ಿಕೊಂಡು
    0.38
    ę
    0.38
     dentre
    0.38
     gubit
    0.38
     අතර
    0.37
     bijvoorbeeld
    0.37
     wśród
    0.37
    ґ
    0.37
    রুদ্ধ
    0.37
    POSITIVE LOGITS
    两种
    0.44
    兩種
    0.41
     collectionView
    0.38
     પ્રો
    0.38
    Dv
    0.37
     النهائية
    0.36
    有两种
    0.35
    DFS
    0.35
     kaldığımız
    0.35
    卒
    0.35
    Activations Density 0.030%

    No Known Activations