© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 16011
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    negative words

    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
    ";
    
    -1.91
    ";
    -1.88
    }));
    
    -1.79
    ")));
    -1.77
    ';
    
    -1.74
    ';
    -1.73
    ]));
    
    -1.73
    "]];
    -1.72
    '];
    
    -1.72
    }";
    -1.71
    POSITIVE LOGITS
     tricky
    0.81
     troublesome
    0.79
     nasty
    0.77
     notoriously
    0.74
     harsh
    0.72
     embarrassing
    0.72
     treacherous
    0.71
     tough
    0.69
     frightening
    0.69
     daunting
    0.69
    Activations Density 1.521%

    No Known Activations