© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39122
    Prev
    Next
    INDEX
    Explanations

    Location, Swift, rpm, RT, Not

    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_11_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
    clientsdetails
    0.54
     shameful
    0.48
     imprison
    0.47
    എ
    0.47
     వచ్చిన
    0.46
    誢
    0.46
     বাতিল
    0.44
    ümü
    0.44
     scrapped
    0.44
    忽略
    0.44
    POSITIVE LOGITS
    Purch
    0.51
     Laub
    0.45
     Purchasing
    0.45
     Desarrollo
    0.44
     Такая
    0.44
    plaza
    0.44
    ၃
    0.44
     terapia
    0.43
     것은
    0.43
     odp
    0.42
    Activations Density 0.006%

    No Known Activations