© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8255
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming syntax

    oai_token-act-pair · gemini-2.0-flash

    Parenthesis, brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ParallelGroup
    -0.76
    extAlignment
    -0.75
    MLLoader
    -0.71
    DockStyle
    -0.70
    <bos>
    -0.70
    AndEndTag
    -0.68
     NDEBUG
    -0.66
    PMailer
    -0.64
     $_(
    -0.62
    EndProject
    -0.61
    POSITIVE LOGITS
    +#+
    0.54
     سكانية
    0.47
    ManagedBean
    0.38
     Reforma
    0.37
     I
    0.37
    วา
    0.36
     linkovi
    0.36
     Extragalactic
    0.35
    JoinTable
    0.35
     opponent
    0.34
    Activations Density 1.694%

    No Known Activations