© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10280
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and laboratory procedures

    oai_token-act-pair · gemini-2.0-flash

    chemical compound names

    np_token-act-pair-logits · gpt-4o-mini

    Chemistry contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ujednoznacz
    -0.77
     '\\;'
    -0.67
     يتيمه
    -0.66
    SerializedName
    -0.55
    NameInMap
    -0.54
    complexType
    -0.53
    extAlignment
    -0.52
    MemoryWarning
    -0.52
    ValueGenerated
    -0.51
     AssemblyCompany
    -0.50
    POSITIVE LOGITS
     mon
    0.68
     Mon
    0.56
     di
    0.55
     Na
    0.53
    Chunks
    0.52
    írus
    0.51
    beforeSend
    0.49
     Emits
    0.48
    mon
    0.47
     Sag
    0.47
    Activations Density 2.698%

    No Known Activations