© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8793
    Prev
    Next
    INDEX
    Explanations

    references to time, including immediate actions and time-related words.

    oai_token-act-pair · gemini-2.0-flash

    immediate/instant

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     CreateTagHelper
    -0.75
    "),
    -0.73
    [])
    -0.71
    )");
    -0.70
     propOrder
    -0.69
    
    -0.68
     AssemblyCompany
    -0.68
    Personensuche
    -0.67
    bewerken
    -0.66
    )";
    -0.66
    POSITIVE LOGITS
    enumi
    0.53
     acceptez
    0.45
    laf
    0.45
    Quy
    0.43
    transformed
    0.43
    ↺
    0.42
    тиза
    0.41
     >>=
    0.41
     Legg
    0.41
    Stride
    0.40
    Activations Density 12.028%

    No Known Activations