© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 165457
    Prev
    Next
    INDEX
    Explanations

    like or dislike

    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
    де
    0.69
    ون
    0.59
     luce
    0.59
    ાસ
    0.58
    ak
    0.57
    德
    0.57
    ాల
    0.56
    可能
    0.56
    یکی
    0.55
    ━━━━
    0.55
    POSITIVE LOGITS
    ASTIC
    0.63
    ribe
    0.58
    जिया
    0.55
     পর্যাপ্ত
    0.54
    ense
    0.52
     σε
    0.52
    "]:
    0.52
     সাক্ষাৎ
    0.52
     intolerant
    0.52
     Adverse
    0.50
    Activations Density 0.002%

    No Known Activations