© 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. 14633
    Prev
    Next
    INDEX
    Explanations

    technical writing that requires an understanding of math and/or physics including frequent use of the word 'is'.

    oai_token-act-pair · gemini-2.0-flash

    technical writing

    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
    -0.85
     AspNetCore
    -0.66
    },[])
    -0.60
    )_/¯
    -0.59
    ")));
    
    -0.57
     "}";
    -0.56
    )"),
    -0.56
    }();
    -0.56
    }
    
    
    -0.55
    }),
    
    -0.55
    POSITIVE LOGITS
    adaptiveStyles
    0.59
    WebElementEntity
    0.52
    Collegamenti
    0.52
     gambe
    0.52
     Pascual
    0.52
     BeautifulSoup
    0.50
     rectification
    0.49
     matrícula
    0.49
     giudi
    0.49
    parsedMessage
    0.47
    Activations Density 11.733%

    No Known Activations