© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 2097
    Prev
    Next
    INDEX
    Explanations

    instances of assistance, personal pronouns, and auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    Helping others

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ]));
    
    -0.77
    )";
    
    -0.73
    }]);
    -0.70
    styleable
    -0.69
    ")));
    
    -0.69
    >");
    
    -0.68
    }))
    
    -0.67
    })),
    -0.66
    ')]
    -0.65
    '])){
    
    -0.65
    POSITIVE LOGITS
     out
    0.77
     complete
    0.74
     intptr
    0.63
    
    0.61
    didSet
    0.60
     in
    0.52
    complete
    0.52
    wnątrz
    0.52
     as
    0.51
     express
    0.50
    Activations Density 5.586%

    No Known Activations