© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13290
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, recognizing numbers, variables, and operations.

    oai_token-act-pair · gemini-2.0-flash

    mathematical operations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     GenerationType
    -0.83
    RenderAtEndOf
    -0.77
    DoubleQuotes
    -0.73
    IntoConstraints
    -0.71
    
    -0.70
    tvguidetime
    -0.69
    GEBURTSDATUM
    -0.68
     onPostExecute
    -0.68
    \{\\
    -0.68
    Rhestr
    -0.65
    POSITIVE LOGITS
    UrlResolution
    0.49
    ũ
    0.49
     berle
    0.48
    Geplaatst
    0.46
    стема
    0.45
     lud
    0.41
    Personendaten
    0.41
     Papst
    0.41
    ToTop
    0.41
    рал
    0.41
    Activations Density 0.622%

    No Known Activations