© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20216
    Prev
    Next
    INDEX
    Explanations

    summarize different scripts

    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_56_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
    身
    1.13
    身的
    0.90
     身
    0.77
     thân
    0.75
    ตัว
    0.68
     body
    0.63
    身为
    0.61
    ீ
    0.58
    body
    0.57
     Body
    0.55
    POSITIVE LOGITS
    খ্যাত
    0.42
    ப்பு
    0.37
     خاط
    0.37
    oba
    0.37
    தியே
    0.36
    пусти
    0.36
    UpSync
    0.36
    JobID
    0.36
    தியில்
    0.35
    чника
    0.35
    Activations Density 0.003%

    No Known Activations