© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12110
    Prev
    Next
    INDEX
    Explanations

    lines of code or build scripts related to creating installers

    oai_token-act-pair · gemini-2.0-flash

    Software installation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    MigrationBuilder
    -0.68
    UnusedPrivate
    -0.63
    SPJ
    -0.60
    AndEndTag
    -0.58
    GOTREF
    -0.57
    InitVars
    -0.56
    Kritik
    -0.54
    UpInside
    -0.52
    UrlResolution
    -0.52
    essor
    -0.51
    POSITIVE LOGITS
     Setup
    0.88
    Setup
    0.85
     setup
    0.85
    setup
    0.84
     SETUP
    0.76
     setups
    0.67
    SETUP
    0.60
    rån
    0.50
    msi
    0.47
    
    0.46
    Activations Density 2.281%

    No Known Activations