© 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. 5037
    Prev
    Next
    INDEX
    Explanations

    the syntax of coding languages and mathematical formulas.

    oai_token-act-pair · gemini-2.0-flash

    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
     chofe
    -0.82
     Eſ
    -0.76
    سكرية
    -0.76
     Efq
    -0.76
     uſed
    -0.74
    ammans
    -0.74
     Jefus
    -0.73
     poffible
    -0.73
     myſelf
    -0.72
     Chaves
    -0.72
    POSITIVE LOGITS
     resourceCulture
    0.54
     تضيفلها
    0.50
    +:+
    0.48
     onCancelled
    0.48
    XmlEnum
    0.47
    XmlAccessType
    0.47
    AndEndTag
    0.46
    windowFixed
    0.46
    bmod
    0.45
    complexType
    0.45
    Activations Density 2.304%

    No Known Activations