© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 12419
    Prev
    Next
    INDEX
    Explanations

    complex math equations and code snippets.

    oai_token-act-pair · gemini-2.0-flash

    code/math expressions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    '));
    -0.60
    onAttach
    -0.58
    tiness
    -0.58
    ."));
    -0.57
    "));
    -0.56
     ThemeData
    -0.56
    theless
    -0.51
     pathlib
    -0.51
     Injectable
    -0.48
     CanadaChoose
    -0.48
    POSITIVE LOGITS
     };
    0.68
    __(/*!
    0.65
     };
    
    0.61
    };
    0.61
     betweenstory
    0.61
    ;
    
    0.60
    ,:);
    0.57
     *);
    0.54
    };
    
    0.54
    SuspendLayout
    0.54
    Activations Density 1.980%

    No Known Activations