© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12361
    Prev
    Next
    INDEX
    Explanations

    LaTeX array environments

    oai_token-act-pair · gemini-2.0-flash

    ll

    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
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.84
    EndGlobalSection
    -0.71
    DockStyle
    -0.65
    extAlignment
    -0.65
    InputBorder
    -0.63
     Signalez
    -0.62
    FieldNumber
    -0.61
    contentLoaded
    -0.60
     '{@
    -0.60
     Khart
    -0.60
    POSITIVE LOGITS
    PageIndex
    0.64
    Abp
    0.60
    //
    0.58
    éal
    0.57
    mstyle
    0.55
    etyl
    0.50
    olum
    0.50
    olition
    0.50
    áš
    0.50
    טר
    0.49
    Activations Density 1.653%

    No Known Activations