© 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. 3412
    Prev
    Next
    INDEX
    Explanations

    time-related words associated with processes, requests, or tasks

    oai_token-act-pair · gemini-2.0-flash

    future events

    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
     hours
    -0.77
     years
    -0.74
     days
    -0.68
     months
    -0.67
     weeks
    -0.66
     Hours
    -0.65
    Years
    -0.65
    hours
    -0.64
     horas
    -0.63
    Hours
    -0.62
    POSITIVE LOGITS
    sizeCache
    0.76
    UrlResolution
    0.76
     '\\;'
    0.74
    脚注の使い方
    0.73
     يتيمه
    0.72
    fjspx
    0.69
    istoitu
    0.68
     Administrativna
    0.68
    Cyfeiriadau
    0.67
     للاسماء
    0.67
    Activations Density 2.281%

    No Known Activations