© 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. 11676
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially C++ code with matrix or vector operations

    oai_token-act-pair · gemini-2.0-flash

    Code and data structures

    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
     Administrativna
    -0.80
    期刊论文
    -0.66
     الرياضيه
    -0.66
    WebVitals
    -0.66
    rrggbb
    -0.63
    AnchorStyles
    -0.61
    Gweler
    -0.60
    IndentedString
    -0.60
    EDEFAULT
    -0.60
    neurial
    -0.60
    POSITIVE LOGITS
    Stride
    0.60
    tensors
    0.50
    dtype
    0.50
    Dims
    0.46
     dtype
    0.46
    strides
    0.46
    ayout
    0.45
    astype
    0.45
     berper
    0.44
     parades
    0.44
    Activations Density 12.391%

    No Known Activations