© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11577
    Prev
    Next
    INDEX
    Explanations

    the words "trail" and "conservative," often in the context of political and geographical topics

    oai_token-act-pair · gemini-2.0-flash

    trails or conservatism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Efq
    -1.29
     myſelf
    -1.27
    WebVitals
    -1.24
     itſelf
    -1.13
    Vidite
    -1.13
     nahilalakip
    -1.13
    Geplaatst
    -1.11
     himſelf
    -1.09
    ſelves
    -1.06
     démocr
    -1.06
    POSITIVE LOGITS
     
    0.94
    ,
    0.74
     "
    0.73
     '
    0.73
    ↵↵
    0.71
    .
    0.65
    :
    0.64
    骨
    0.64
     bak
    0.63
    1
    0.62
    Activations Density 2.275%

    No Known Activations