© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14440
    Prev
    Next
    INDEX
    Explanations

    a variety of words associated with possession, location, electronics, being naked, or family.

    oai_token-act-pair · gemini-2.0-flash

    Social groups

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    DockStyle
    -0.80
     selves
    -0.79
     careers
    -0.77
     bodies
    -0.76
     personalities
    -0.75
    bodies
    -0.72
     Bodies
    -0.71
     natures
    -0.71
    Bodies
    -0.71
    minds
    -0.71
    POSITIVE LOGITS
     bands
    0.65
     galleries
    0.62
     clubs
    0.62
     sectors
    0.61
     chapters
    0.59
     faculties
    0.59
     channels
    0.59
    ications
    0.58
     breweries
    0.58
     quarries
    0.58
    Activations Density 3.250%

    No Known Activations