© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3295
    Prev
    Next
    INDEX
    Explanations

    mentions of clarity, integration, and conflict.

    oai_token-act-pair · gemini-2.0-flash

    clear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.98
     الحره
    -0.94
    transQ
    -0.87
    principalColumn
    -0.84
    tonode
    -0.84
     newOwner
    -0.82
    fjspx
    -0.81
     ویکی‌پدیا
    -0.81
     rentrée
    -0.80
     IBOutlet
    -0.80
    POSITIVE LOGITS
    o
    0.70
    ↵
    0.66
    <eos>
    0.62
     
    0.58
    e
    0.57
    x
    0.56
      
    0.56
    ,
    0.55
    ↵↵
    0.53
    copes
    0.53
    Activations Density 1.117%

    No Known Activations