© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11240
    Prev
    Next
    INDEX
    Explanations

    the word "time" and sometimes ages

    oai_token-act-pair · gemini-2.0-flash

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     impianti
    -0.53
    openqa
    -0.51
    ISupport
    -0.50
     iconst
    -0.47
     moldura
    -0.46
     tênis
    -0.46
     níveis
    -0.46
     asciug
    -0.45
    ActionEvent
    -0.45
     almoço
    -0.45
    POSITIVE LOGITS
    <bos>
    0.87
    ########.
    0.76
    InitVars
    0.74
     Италијани
    0.69
    <thead>
    0.64
    λικά
    0.59
    thwaite
    0.59
     reschedule
    0.58
     kasarigan
    0.58
    Hochspringen
    0.57
    Activations Density 0.377%

    No Known Activations