© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4462
    Prev
    Next
    INDEX
    Explanations

    mentions of the general public, especially in relation to society

    oai_token-act-pair · gemini-2.0-flash

    common or ordinary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    RTLD
    -0.63
    forChild
    -0.63
     useRouter
    -0.61
    SharedDtor
    -0.61
    LabelTagHelper
    -0.60
     gynhyrchwyd
    -0.57
     Rais
    -0.56
    ONESIA
    -0.54
     BoxDecoration
    -0.54
     Huskies
    -0.52
    POSITIVE LOGITS
     common
    1.25
     ordinary
    1.22
    common
    1.07
    ordinary
    0.98
     plebe
    0.97
     COMMON
    0.96
     Common
    0.96
    Ordinary
    0.95
     zwyk
    0.93
    Common
    0.91
    Activations Density 1.372%

    No Known Activations