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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13765
    Prev
    Next
    INDEX
    Explanations

    horizontal separators and forward/reply markers in emails and forum posts

    oai_token-act-pair · gemini-2.0-flash

    ------

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ...
    -0.65
    …
    -0.65
    ....
    -0.52
    ..
    -0.50
    vich
    -0.47
    ….
    -0.46
    prits
    -0.45
     ...
    -0.44
    stras
    -0.43
     cl
    -0.42
    POSITIVE LOGITS
    ########.
    0.90
    })*/
    0.79
    });*/
    0.75
    AnimationsModule
    0.73
    "]];
    0.73
    }*/
    
    0.71
    '])){
    
    0.71
     OFDb
    0.70
     NSCoder
    0.70
    '));
    
    0.69
    Activations Density 3.472%

    No Known Activations