© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9743
    Prev
    Next
    INDEX
    Explanations

    code and commands

    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_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -1.14
     AssemblyTitle
    -0.68
    ಒ
    -0.66
    SourceChecksum
    -0.65
    SharedCtor
    -0.65
     lenker
    -0.65
    ributions
    -0.62
    NUMX
    -0.59
    eleste
    -0.59
     Descriptors
    -0.59
    POSITIVE LOGITS
     continuant
    0.49
     prouver
    0.47
    indelijk
    0.46
    StringVar
    0.46
     hội
    0.45
    ține
    0.45
    URNS
    0.44
    höhe
    0.44
    FontOfSize
    0.44
    ENGTH
    0.43
    Activations Density 2.584%

    No Known Activations