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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 13443
    Prev
    Next
    INDEX
    Explanations

    words that commonly precede or modify negative situations or people

    oai_token-act-pair · gemini-2.0-flash

    code special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     frightening
    -0.70
     harsh
    -0.69
     painful
    -0.69
     embarrassing
    -0.69
     terrifying
    -0.68
     treacherous
    -0.68
     troublesome
    -0.68
     nakalista
    -0.66
     scary
    -0.66
     nasty
    -0.66
    POSITIVE LOGITS
    ")));
    1.61
    ";
    1.54
    ";
    
    1.52
    "]];
    1.45
    )";
    1.43
    ')));
    1.43
    ]";
    1.42
    }";
    1.40
    ")));
    
    1.38
    "));
    1.37
    Activations Density 5.363%

    No Known Activations