© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 218703
    Prev
    Next
    INDEX
    Explanations

    repeatedly pulsed presented men integer 5 (

    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_16_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
     فى
    0.47
    pyplot
    0.46
     lattice
    0.46
    شاف
    0.42
    equilib
    0.42
     ]:
    0.42
    <0xB0>
    0.41
     Prob
    0.41
    √
    0.41
    皮
    0.41
    POSITIVE LOGITS
    StudentRecord
    0.52
    ковых
    0.52
     inade
    0.52
    দিগকে
    0.51
     hMut
    0.50
    idora
    0.50
     tekan
    0.49
     اشک
    0.49
    नेश
    0.49
     sering
    0.49
    Activations Density 0.000%

    No Known Activations