© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5894
    Prev
    Next
    INDEX
    Explanations

    keys and values from code

    oai_token-act-pair · gemini-2.0-flash

    apostrophe/quote

    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
     للاسماء
    -0.77
     CreateTagHelper
    -0.66
    arrings
    -0.65
    ectady
    -0.64
     Réponses
    -0.64
    enschappelijke
    -0.63
     يتيمه
    -0.63
    Ӕ
    -0.63
    KommentareTeilen
    -0.62
     surla
    -0.62
    POSITIVE LOGITS
    "]);
    
    1.05
    ()]);
    0.89
    "]);
    0.88
    ']);
    
    0.87
     ]);
    0.86
    "])
    
    0.86
    ()));
    
    0.85
    "];
    
    0.84
    '));
    
    0.82
    )");
    
    0.82
    Activations Density 3.120%

    No Known Activations