© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4590
    Prev
    Next
    INDEX
    Explanations

    code blocks, especially related to data structures and parsing

    oai_token-act-pair · gemini-2.0-flash

    Code, programming

    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
    5
    -1.05
    8
    -0.75
    7
    -0.73
    6
    -0.65
    9
    -0.64
    ５
    -0.58
     пяти
    -0.56
    五
    -0.56
    3
    -0.53
     five
    -0.52
    POSITIVE LOGITS
    ScopeManager
    0.66
    rawDesc
    0.63
     незавершена
    0.63
    DockStyle
    0.62
    writeFieldEnd
    0.60
    /**
    0.59
     snippetHide
    0.58
    WithIOException
    0.58
     Thine
    0.57
    \{\\
    0.57
    Activations Density 0.712%

    No Known Activations