© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1694
    Prev
    Next
    INDEX
    Explanations

    proper nouns, names, or possible name parts

    oai_token-act-pair · gemini-2.0-flash

    Code and programming snippets

    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
    utes
    -0.43
    nis
    -0.41
    ily
    -0.41
     charge
    -0.40
    ned
    -0.40
    ud
    -0.38
    fa
    -0.38
    ty
    -0.36
     de
    -0.36
    hafte
    -0.36
    POSITIVE LOGITS
    \{\\
    0.88
    хьтан
    0.88
    IndentedString
    0.85
     Meksiku
    0.83
     <<<<<<<<<<<<<<
    0.81
     <>",
    0.79
    IsContent
    0.79
    Демографія
    0.77
     CreateTagHelper
    0.75
     المعيارى
    0.75
    Activations Density 0.533%

    No Known Activations