© 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. 3177
    Prev
    Next
    INDEX
    Explanations

    hyphenated words ending in a variant of "ate" or "ed".

    oai_token-act-pair · gemini-2.0-flash

    related

    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
     idéia
    -0.89
     venait
    -0.80
     perchè
    -0.77
     poichè
    -0.77
     auroit
    -0.76
     Etats
    -0.75
     normaux
    -0.74
     dedans
    -0.74
     diatas
    -0.73
     feroit
    -0.72
    POSITIVE LOGITS
    ]")
    0.90
    )");
    
    0.90
    .')
    0.89
    .],
    0.89
    ]')
    0.88
    ')";
    0.85
    ’).
    0.84
    )";
    
    0.84
    ’)
    0.84
    ')]
    0.83
    Activations Density 1.714%

    No Known Activations