© 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. 5881
    Prev
    Next
    INDEX
    Explanations

    subjective and emotive language, particularly in quoted speech

    oai_token-act-pair · gemini-2.0-flash

    Angry internet commentary

    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
    parsedMessage
    -0.69
     nakalista
    -0.59
    Personensuche
    -0.57
     Initialise
    -0.56
    styleType
    -0.54
    mises
    -0.53
     kaarangay
    -0.51
    AddField
    -0.51
     Şi
    -0.50
    XmlAccessorType
    -0.49
    POSITIVE LOGITS
    AndEndTag
    0.58
     générations
    0.53
     Pank
    0.53
     AttributeSet
    0.53
    BackStack
    0.52
     sabbia
    0.51
    erdings
    0.51
     pheasant
    0.49
     crossorigin
    0.48
    invokeLater
    0.48
    Activations Density 5.006%

    No Known Activations