© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261358
    Prev
    Next
    INDEX
    Explanations

    Higarika School or Austria-Hungary

    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
    ри
    1.34
    ع
    1.34
    ك
    1.34
    ра
    1.27
    ва
    1.22
    ت
    1.18
    ق
    1.18
    ما
    1.10
    ü
    1.09
    י
    1.06
    POSITIVE LOGITS
    to
    1.55
    s
    1.51
    ために
    1.26
    نی
    1.23
     powied
    1.22
    तौर
    1.11
     musician
    1.05
     aument
    1.04
     difficoltà
    1.03
    in
    1.02
    Activations Density 0.000%

    No Known Activations