© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10490
    Prev
    Next
    INDEX
    Explanations

    words related to literary analysis, social issues, or philosophical concepts.

    oai_token-act-pair · gemini-2.0-flash

    academic/complex texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    HasForeignKey
    -0.60
    typeorm
    -0.54
     arşivlendi
    -0.54
     Spells
    -0.53
     مشين
    -0.53
     Majefty
    -0.52
    ThroughAttribute
    -0.52
    Espèce
    -0.52
     Assemblies
    -0.52
     Diplo
    -0.51
    POSITIVE LOGITS
    getManager
    0.54
     man
    0.53
     basic
    0.52
    hdessä
    0.52
     
    0.51
     para
    0.49
    czegóły
    0.48
     a
    0.48
     St
    0.48
    ETING
    0.47
    Activations Density 3.452%

    No Known Activations