Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 262062
    Prev
    Next
    INDEX
    Explanations

    interconnectedness

    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_5_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
    </h2>
    1.43
    ется
    1.38
     hairpin
    1.02
    นี้
    1.01
    ยัง
    0.96
    กับ
    0.94
     warten
    0.94
     instancia
    0.93
    </h3>
    0.92
     pedra
    0.91
    POSITIVE LOGITS
    ע
    1.52
    ade
    1.45
    =\
    1.43
    ع
    1.31
    =\{
    1.30
    uts
    1.29
    علم
    1.28
    ح
    1.28
    ك
    1.28
    ()
    1.27
    Activations Density 0.001%

    No Known Activations