© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1851
    Prev
    Next
    INDEX
    Explanations

    critical reviews of dark fiction, often mentioning Australia

    oai_token-act-pair · gemini-2.0-flash

    book excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     AssemblyTitle
    -0.47
    nodoc
    -0.45
     AttributeSet
    -0.42
    XmlType
    -0.36
    XmlSchema
    -0.35
    ridis
    -0.34
     Businesses
    -0.34
    qxd
    -0.34
     odkazy
    -0.34
    DataAnnotations
    -0.33
    POSITIVE LOGITS
    fromnode
    0.76
    CppMethod
    0.74
    rätt
    0.73
    rungsseite
    0.71
    CodeAttribute
    0.69
    ckså
    0.69
     الحره
    0.66
     disambiguazione
    0.66
     onCreateView
    0.66
    ண்டும்
    0.64
    Activations Density 13.696%

    No Known Activations