© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8280
    Prev
    Next
    INDEX
    Explanations

    code snippets, numbers or symbols, and text fragments related to a software programming context.

    oai_token-act-pair · gemini-2.0-flash

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Référence
    -0.57
     mil
    -0.49
    ye
    -0.43
    httphttps
    -0.43
    AndroidJUnit
    -0.41
    amet
    -0.41
     HR
    -0.40
    ange
    -0.40
    ace
    -0.40
    ongyang
    -0.40
    POSITIVE LOGITS
     Efq
    0.77
     itſelf
    0.75
     MainAxisSize
    0.74
     pleaſure
    0.71
     Majefty
    0.71
     myſelf
    0.70
     preſent
    0.68
     themſelves
    0.68
    endphp
    0.67
     Eſ
    0.67
    Activations Density 2.731%

    No Known Activations