© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15636
    Prev
    Next
    INDEX
    Explanations

    code snippets, directories, and file paths

    oai_token-act-pair · gemini-2.0-flash

    words related to drives

    np_token-act-pair-logits · gpt-4o-mini

    drive

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Monro
    -0.50
    "]();
    -0.49
     Sandman
    -0.48
     vascular
    -0.47
    ROLES
    -0.47
     malt
    -0.46
    ensement
    -0.46
     Tul
    -0.46
     mutate
    -0.46
     Rasul
    -0.45
    POSITIVE LOGITS
     drive
    1.17
     hard
    1.07
     drives
    1.03
     Drive
    0.98
    drive
    0.94
    Drive
    0.90
     Hard
    0.88
     Drives
    0.87
    Hard
    0.87
    drives
    0.84
    Activations Density 3.494%

    No Known Activations