© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6639
    Prev
    Next
    INDEX
    Explanations

    the word "sensitive"

    oai_token-act-pair · gemini-2.0-flash

    sensitive

    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
     Jurí
    -0.67
    ordinaire
    -0.65
    ENGTH
    -0.65
     Especial
    -0.63
     spotlight
    -0.62
    ÁT
    -0.62
     Untersch
    -0.60
     outre
    -0.60
    izie
    -0.59
     privil
    -0.59
    POSITIVE LOGITS
    %");
    0.74
    `),
    0.72
    expandindo
    0.70
    <bos>
    0.69
    ’).
    0.69
    )";
    
    0.69
    %")
    0.66
    %"),
    0.66
    PreferredItem
    0.65
    ?')
    0.64
    Activations Density 1.012%

    No Known Activations