Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11206
    Prev
    Next
    INDEX
    Explanations

    code relating to multithreading and table manipulation in Swift for Apple products

    oai_token-act-pair · gemini-2.0-flash

    punctuation and language markers

    np_token-act-pair-logits · gpt-4o-mini

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     المعيارى
    -0.59
    AddTagHelper
    -0.52
    )";
    
    -0.49
    }")]
    -0.49
    igual
    -0.49
    HtmlAttribute
    -0.48
     mucho
    -0.48
    Бахар
    -0.48
    }));
    
    -0.47
    ResponseStatus
    -0.46
    POSITIVE LOGITS
     as
    1.40
     sebagai
    0.82
     как
    0.75
     као
    0.74
    !.
    0.73
    作为
    0.71
    !,
    0.70
    !;
    0.70
    !”.
    0.68
    !?
    0.66
    Activations Density 2.004%

    No Known Activations