© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14186
    Prev
    Next
    INDEX
    Explanations

    words related to the history of Denmark and Germany

    oai_token-act-pair · gemini-2.0-flash

    Cultural/linguistic identity and heritage

    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
     SwiftUI
    -0.57
    SupportActionBar
    -0.54
    openqa
    -0.54
    BufferException
    -0.53
    AnimationsModule
    -0.52
    GINIA
    -0.52
    textAppearance
    -0.51
    tvguidetime
    -0.48
     CharSequence
    -0.48
    Fordítás
    -0.47
    POSITIVE LOGITS
     مرئيه
    0.76
     type
    0.66
     types
    0.63
    ksikon
    0.59
    type
    0.57
     correctes
    0.57
    ValueStyle
    0.56
    expandindo
    0.54
    contentLoaded
    0.53
     Us
    0.52
    Activations Density 2.501%

    No Known Activations