© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1146
    Prev
    Next
    INDEX
    Explanations

    words in scientific papers that describe mechanical stress and strain

    oai_token-act-pair · gemini-2.0-flash

    shear stress and flow

    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
    -0.83
    참고
    -0.73
    urably
    -0.69
    Geplaatst
    -0.68
    Personendaten
    -0.68
     Hesper
    -0.65
    ocracy
    -0.64
     Archae
    -0.63
     mergeFrom
    -0.63
    phro
    -0.62
    POSITIVE LOGITS
    čník
    0.40
     szár
    0.39
     temprano
    0.38
    にご
    0.38
    SuspendLayout
    0.36
     bocca
    0.36
     néz
    0.36
     reserve
    0.35
     aload
    0.35
     suasana
    0.35
    Activations Density 2.934%

    No Known Activations