© 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. 14488
    Prev
    Next
    INDEX
    Explanations

    words related to situations of public unrest, like political disputes, religious objections, or international trade disagreements.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "over"

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

    over

    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
    LookAnd
    -1.03
    WebVitals
    -0.85
     мәкал
    -0.73
    AnchorTagHelper
    -0.73
     Roskov
    -0.71
    دانشنامهٔ
    -0.69
     typelib
    -0.67
     فريبيس
    -0.66
     незавершена
    -0.66
    DockStyle
    -0.65
    POSITIVE LOGITS
     over
    3.22
    over
    2.44
    Over
    2.31
     Over
    2.30
     OVER
    2.13
     över
    1.94
    OVER
    1.82
     über
    1.69
    overs
    1.48
    オーバー
    1.47
    Activations Density 2.049%

    No Known Activations