© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12903
    Prev
    Next
    INDEX
    Explanations

    words and phrases referring to the passage of time or next steps

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'from'

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

    "from"

    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
     jsPsych
    -0.74
     EconPapers
    -0.69
     '\\;'
    -0.68
    aarrggbb
    -0.68
    expandindo
    -0.66
    AnchorTagHelper
    -0.65
     kaarangay
    -0.64
    verwijspagina
    -0.63
    ChildScrollView
    -0.63
     InputDecoration
    -0.60
    POSITIVE LOGITS
     from
    2.77
    from
    2.22
     FROM
    2.03
     From
    2.00
    From
    1.96
     từ
    1.83
    FROM
    1.75
     dari
    1.73
     från
    1.73
     desde
    1.70
    Activations Density 3.178%

    No Known Activations