© 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. 7042
    Prev
    Next
    INDEX
    Explanations

    a mix of code-related tokens, including paths, variables, and arithmetic operators, as well as exponential notation

    oai_token-act-pair · gemini-2.0-flash

    code, math, file paths

    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
     +
    -0.84
     surla
    -0.77
    Cyfarwyddwr
    -0.72
    Personensuche
    -0.71
    CppMethod
    -0.71
     =
    -0.68
     تانيه
    -0.68
     createState
    -0.66
    曖昧さ回避
    -0.65
     AssemblyTitle
    -0.65
    POSITIVE LOGITS
     (--
    0.45
     klokken
    0.45
    zembro
    0.45
    (::
    0.44
    ->
    0.44
    |>
    0.43
     (%
    0.43
    ,:
    0.42
    ),'
    0.42
    mercy
    0.41
    Activations Density 4.897%

    No Known Activations