© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 11504
    Prev
    Next
    INDEX
    Explanations

    words associated with processes of change, instability, or failure in scientific or economic contexts

    oai_token-act-pair · gemini-2.0-flash

    dependencies, changes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    UnsafeEnabled
    -0.73
    extAlignment
    -0.73
     bezeichneter
    -0.69
    RenderAtEndOf
    -0.66
    LLocation
    -0.66
    AutoresizingMask
    -0.65
     resourceCulture
    -0.65
    WriteBarrier
    -0.64
     ModelExpression
    -0.63
    #+#
    -0.63
    POSITIVE LOGITS
     of
    1.58
     của
    1.02
    ของ
    0.91
    of
    0.73
     ofthe
    0.71
    ofthe
    0.66
     των
    0.66
     ของ
    0.63
     Of
    0.62
     της
    0.62
    Activations Density 1.872%

    No Known Activations