© 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. 3573
    Prev
    Next
    INDEX
    Explanations

    negation, school grades, and legal/official terms

    oai_token-act-pair · gemini-2.0-flash

    neither

    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
    -2.09
     Theſe
    -1.98
     myſelf
    -1.91
     autorytatywna
    -1.86
     Monfieur
    -1.83
     Савезне
    -1.82
     ―――――
    -1.78
     itſelf
    -1.77
     Anſ
    -1.76
    StoryboardSegue
    -1.71
    POSITIVE LOGITS
     
    1.14
    ,
    1.11
     (
    0.97
     \
    0.96
     a
    0.95
     so
    0.95
      
    0.94
     D
    0.92
     R
    0.89
     is
    0.88
    Activations Density 2.097%

    No Known Activations