© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14886
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and statutes

    oai_token-act-pair · gemini-2.0-flash

    Legal citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    st
    -2.28
     st
    -2.16
    ST
    -1.63
    St
    -1.42
     ST
    -1.35
     St
    -1.30
    stg
    -1.06
    stur
    -1.05
    sts
    -1.05
    stt
    -1.05
    POSITIVE LOGITS
    IsContent
    0.66
     AssemblyCulture
    0.65
    ItemBackground
    0.63
     AssemblyProduct
    0.60
     ddelweddau
    0.59
    BeginContext
    0.57
     Infórmanos
    0.55
    DockStyle
    0.54
    EndGlobalSection
    0.54
    UserScript
    0.53
    Activations Density 3.423%

    No Known Activations