© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15585
    Prev
    Next
    INDEX
    Explanations

    physics concepts related to particle movement and energy

    oai_token-act-pair · gemini-2.0-flash

    physics/scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    lapsingToolbar
    -0.56
     el
    -0.54
    urlopen
    -0.53
     urllib
    -0.47
    bibitem
    -0.47
    StackNavigator
    -0.45
     CURLOPT
    -0.44
    FormTagHelper
    -0.44
    ViewFeatures
    -0.43
     Cat
    -0.43
    POSITIVE LOGITS
     يتيمه
    0.68
     Lordships
    0.63
     Besoin
    0.61
     itſelf
    0.59
    tonode
    0.59
    ConstraintMaker
    0.58
     Nimbus
    0.56
     TextAlign
    0.56
    calientes
    0.55
     Braid
    0.55
    Activations Density 3.364%

    No Known Activations