© 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. 8108
    Prev
    Next
    INDEX
    Explanations

    language about medical studies

    oai_token-act-pair · gemini-2.0-flash

    Technical/legal text

    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
    Not in Any Lists

    No Comments

    Negative Logits
     برانيه
    -0.54
    ztes
    -0.51
     held
    -0.50
     typelib
    -0.50
    iseta
    -0.49
    maco
    -0.48
    permitAll
    -0.48
    indicator
    -0.47
    ÁT
    -0.47
    OSIS
    -0.47
    POSITIVE LOGITS
     متعلقه
    0.78
    ::_('
    0.75
    ScopeManager
    0.65
     disqual
    0.64
     SEDS
    0.62
     disambiguazione
    0.60
    WebVitals
    0.60
    tvguidetime
    0.60
    PerformLayout
    0.58
     yoox
    0.54
    Activations Density 14.959%

    No Known Activations