© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10776
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands

    oai_token-act-pair · gemini-2.0-flash

    LaTeX code and bibliography

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     elä
    -0.42
    vana
    -0.39
     grå
    -0.39
     tõ
    -0.39
    Demos
    -0.38
     objetivos
    -0.38
     rând
    -0.38
     Hahn
    -0.37
    虚
    -0.37
     ren
    -0.36
    POSITIVE LOGITS
     Normdatei
    0.91
     EconPapers
    0.85
    Tikang
    0.79
     ProtoMessage
    0.78
    OCCURRED
    0.78
     propOrder
    0.75
     AssemblyTitle
    0.73
    IntoConstraints
    0.72
    argout
    0.71
    Enllaces
    0.71
    Activations Density 0.339%

    No Known Activations