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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 165548
    Prev
    Next
    INDEX
    Explanations

    language syntax errors

    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_13_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
    K
    0.38
     khảo
    0.37
    ర్
    0.36
     آ
    0.36
     ka
    0.35
    нд
    0.34
    ka
    0.33
    line
    0.33
    、
    0.33
    0
    0.32
    POSITIVE LOGITS
    ív
    0.38
     காட்ச
    0.35
    ellington
    0.35
     दिरहम
    0.34
    ümer
    0.34
    ileri
    0.34
     outfitted
    0.34
    ordia
    0.33
     사이즈
    0.33
     synced
    0.33
    Activations Density 0.005%

    No Known Activations