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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 201257
    Prev
    Next
    INDEX
    Explanations

    rap artists like Nas and Outkast

    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_12_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
     O
    0.50
     trajectory
    0.50
     njegov
    0.50
     n
    0.48
    簍
    0.47
     incentiv
    0.47
     dope
    0.46
     calcul
    0.45
     çağ
    0.45
     behest
    0.44
    POSITIVE LOGITS
    }))
    0.46
     பயன்படுகிறது
    0.44
     ผ้า
    0.44
     좋습니다
    0.43
     ஒன்று
    0.42
     والسلام
    0.42
    笔记本
    0.41
     psychotherapy
    0.40
    linen
    0.40
     प्रीमियम
    0.40
    Activations Density 0.001%

    No Known Activations