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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4344
    Prev
    Next
    INDEX
    Explanations

    code and programming related words

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.67
    ↵↵
    -0.67
     is
    -0.60
     and
    -0.60
    '
    -0.56
    The
    -0.52
    <eos>
    -0.52
    An
    -0.51
    ’
    -0.49
    ↵
    -0.48
    POSITIVE LOGITS
    ConstraintMaker
    1.12
     CreateTagHelper
    1.01
     متعلقه
    0.99
    WriteTagHelper
    0.99
    WithIOException
    0.96
     BoxFit
    0.93
    enumi
    0.93
     "..\..\
    0.92
     betweenstory
    0.92
    tagHelperRunner
    0.90
    Activations Density 1.689%

    No Known Activations