© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3049
    Prev
    Next
    INDEX
    Explanations

    truncated text

    oai_token-act-pair · gemini-2.0-flash

    document snippets

    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
    Negative Logits
     Theſe
    -1.16
     Squal
    -1.11
     AssemblyCompany
    -1.10
    StoryboardSegue
    -1.10
     NSCoder
    -1.10
    ftagPool
    -1.07
     Anſ
    -1.07
     Efq
    -1.05
     Monfieur
    -1.02
    expandindo
    -1.01
    POSITIVE LOGITS
     and
    0.83
     or
    0.82
     an
    0.80
     the
    0.76
     all
    0.75
     in
    0.72
     with
    0.69
     (
    0.69
     a
    0.65
     as
    0.65
    Activations Density 0.261%

    No Known Activations