© 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. 10009
    Prev
    Next
    INDEX
    Explanations

    words expressing strong negative emotions, especially anger and revenge

    oai_token-act-pair · gemini-2.0-flash

    anger revenge

    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
    "],
    -0.88
    .";
    -0.87
    ]]
    -0.87
    ...');
    -0.87
    "},
    -0.85
    !")
    -0.85
    ...");
    -0.85
    ]),
    -0.84
    ".
    -0.84
     =",
    -0.84
    POSITIVE LOGITS
    <bos>
    2.52
    ↵↵
    1.05
    ↵
    0.96
    '
    0.90
    ’
    0.77
    1
    0.66
    2
    0.60
    By
    0.57
    The
    0.56
    S
    0.55
    Activations Density 1.112%

    No Known Activations