© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 3002
    Prev
    Next
    INDEX
    Explanations

    the word "true," sometimes in combination with related words like "filled," "joined," "while," or when discussing lengths of time.

    oai_token-act-pair · gemini-2.0-flash

    true

    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
    Negative Logits
     ſmall
    -0.91
    ."));
    -0.91
     myſelf
    -0.89
     themſelves
    -0.88
    )");
    
    -0.87
    ]$}
    -0.87
    "]);
    
    -0.83
     reaſon
    -0.82
    })*/
    -0.82
     Theſe
    -0.82
    POSITIVE LOGITS
     manteiga
    0.51
     addSubview
    0.51
     Brenn
    0.50
    —
    0.50
    saraba
    0.49
    ContentAlignment
    0.48
    o
    0.48
     referirse
    0.47
    zlich
    0.47
     salespeople
    0.47
    Activations Density 0.406%

    No Known Activations