© 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. 303
    Prev
    Next
    INDEX
    Explanations

    Java and Android code snippets, including import statements and XML-like configuration structures

    oai_token-act-pair · gemini-2.0-flash

    Semicolons

    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
    =?,
    -0.53
    :?
    -0.49
    =?
    -0.48
    ]?
    -0.47
    -.-
    -0.47
    TRC
    -0.46
     怎样
    -0.46
    ervlak
    -0.45
    ,
    -0.43
    ==-
    -0.43
    POSITIVE LOGITS
    WebVitals
    0.84
    
    0.73
    ReusableCell
    0.71
    CodeAttribute
    0.71
    StoryboardSegue
    0.71
     typelib
    0.70
     AssemblyCulture
    0.69
     unknownFields
    0.66
    SourceChecksum
    0.62
    iNdEx
    0.61
    Activations Density 8.330%

    No Known Activations