© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13553
    Prev
    Next
    INDEX
    Explanations

    architectural terms and building features

    oai_token-act-pair · gemini-2.0-flash

    ceilings and arches

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     carcin
    -0.49
     platforms
    -0.48
    isAlive
    -0.46
    quillas
    -0.46
    Населення
    -0.46
     platform
    -0.45
    SetActive
    -0.45
    Deck
    -0.45
    ловек
    -0.45
    OrBuilder
    -0.44
    POSITIVE LOGITS
    enumi
    0.75
    \{\\
    0.64
    \}\\
    0.62
    IntoConstraints
    0.59
    Ծանոթ
    0.56
    المكان
    0.56
    AndEndTag
    0.56
     nakalista
    0.53
     henvisninger
    0.53
     ligiloj
    0.53
    Activations Density 0.471%

    No Known Activations