© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1403
    Prev
    Next
    INDEX
    Explanations

    code-related syntax like brackets, operators, and accessors

    oai_token-act-pair · gemini-2.0-flash

    computer code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     
    -0.44
     myſelf
    -0.43
     Dhoni
    -0.41
    ઢ
    -0.40
     themſelves
    -0.40
     poffible
    -0.40
    otras
    -0.40
     Supremo
    -0.39
    ządu
    -0.39
     zood
    -0.39
    POSITIVE LOGITS
    -
    0.84
     pinulongan
    0.71
    mergeFrom
    0.71
    awtextra
    0.69
    setViewportView
    0.66
    EditorBrowsable
    0.66
    -</
    0.64
    -%
    0.63
     typelib
    0.63
     AssemblyCulture
    0.63
    Activations Density 11.852%

    No Known Activations