© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 488
    Prev
    Next
    INDEX
    Explanations

    mentions of evidence and timeline of a crime.

    oai_token-act-pair · gemini-2.0-flash

    day

    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
    Negative Logits
     فريبيس
    -0.96
     виправивши
    -0.93
    
    -0.85
    WebVitals
    -0.76
    PreferredItem
    -0.75
    RenderAtEndOf
    -0.75
     }}"></
    -0.73
    IonicModule
    -0.72
    CppCodeGen
    -0.71
    #+#
    -0.71
    POSITIVE LOGITS
     day
    1.39
     Day
    1.22
    day
    1.10
    Day
    1.09
     DAY
    1.04
    DAY
    0.90
     giorno
    0.85
     ngày
    0.81
    当日
    0.79
     día
    0.79
    Activations Density 1.153%

    No Known Activations