© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6809
    Prev
    Next
    INDEX
    Explanations

    code snippets (likely in C#) with escape characters and parenthesis, also picking up the word "was" and "You"

    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_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
    ]
    -0.62
    ]')
    -0.62
     ']
    -0.59
    .
    -0.59
     _)
    -0.59
    1
    -0.56
     ].
    -0.56
     !}
    -0.54
    ,
    -0.53
     ]
    -0.53
    POSITIVE LOGITS
    setVerticalGroup
    0.84
    +#+
    0.77
    httphttps
    0.75
     مرئيه
    0.73
     CreateTagHelper
    0.73
    发表于
    0.73
    出版年
    0.73
    CodeAttribute
    0.70
    nonatomic
    0.69
     AssemblyProduct
    0.69
    Activations Density 21.317%

    No Known Activations