© 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. 208
    Prev
    Next
    INDEX
    Explanations

    code-related keywords such as variable types and delimiters

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    4
    -0.95
    5
    -0.82
    9
    -0.79
    8
    -0.79
    7
    -0.76
    6
    -0.75
    IndentedString
    -0.69
    2
    -0.64
     Cuatro
    -0.63
     للمعارف
    -0.57
    POSITIVE LOGITS
    AccessorTable
    0.55
    ']?>
    0.50
    [];
    0.49
    ⓧ
    0.49
    "){
    0.49
    /*
    0.48
     doInBackground
    0.48
    "]:
    0.47
    __((
    0.46
    od
    0.46
    Activations Density 7.050%

    No Known Activations