© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14793
    Prev
    Next
    INDEX
    Explanations

    symbols of chemical elements and words related to mining

    oai_token-act-pair · gemini-2.0-flash

    words related to gold

    np_token-act-pair-logits · gpt-4o-mini

    gold and yellow

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    ScopeManager
    -0.99
    StoryboardSegue
    -0.89
     فريبيس
    -0.85
     Shakspeare
    -0.71
    NUMX
    -0.70
    tagHelperRunner
    -0.68
     GenerationType
    -0.68
     againſt
    -0.67
     ***!
    -0.67
    PerformLayout
    -0.66
    POSITIVE LOGITS
     gold
    0.91
     Gold
    0.89
    Gold
    0.77
     GOLD
    0.73
     Yellow
    0.72
    gold
    0.71
     yellow
    0.68
    金
    0.65
    Yellow
    0.65
     Kar
    0.63
    Activations Density 1.551%

    No Known Activations