© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200608
    Prev
    Next
    INDEX
    Explanations

    mocking APIs like typicode

    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_37_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
     Calls
    0.43
     mock
    0.41
    埋
    0.40
    呼び
    0.39
     Calling
    0.39
     സമീപ
    0.39
    多様
    0.38
     calling
    0.37
     Imag
    0.37
     riba
    0.37
    POSITIVE LOGITS
    ّم
    0.41
     brokers
    0.39
    Tis
    0.39
     designates
    0.38
    тельного
    0.38
    ܣ
    0.38
    acul
    0.37
     Designated
    0.37
     designate
    0.35
     Tis
    0.35
    Activations Density 0.002%

    No Known Activations