© 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. 8924
    Prev
    Next
    INDEX
    Explanations

    This neuron attempts to identify the topic of something

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
    culoskeletal
    -0.60
     Ã
    -0.53
    EventLoop
    -0.53
     EconPapers
    -0.52
     ⁠
    -0.49
     -*-
    -0.48
    ofluor
    -0.48
     — 
    -0.47
     

    -0.47
     EnglishChoose
    -0.47
    POSITIVE LOGITS
    ]));
    
    0.78
    ]))
    
    0.71
    ")));
    
    0.65
    ])));
    0.63
    +");
    0.62
    ]));
    0.62
    ])]
    0.60
    ]--;
    0.60
    '];
    
    0.58
    "]))
    0.58
    Activations Density 33.357%

    No Known Activations