© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10810
    Prev
    Next
    INDEX
    Explanations

    LaTeX math environments and the words "equal" or "increases"

    oai_token-act-pair · gemini-2.0-flash

    math, code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    UserScript
    -0.59
    ძ
    -0.47
     referenties
    -0.46
     Allociné
    -0.45
    DeleteBehavior
    -0.45
    COUVER
    -0.45
    ফ
    -0.45
     NgModule
    -0.44
     MonoBehaviour
    -0.44
    TableBody
    -0.43
    POSITIVE LOGITS
     esternos
    0.75
    ContentAsync
    0.69
     صوتيه
    0.61
     protoimpl
    0.60
    MemoryWarning
    0.59
    EndContext
    0.58
     때문
    0.57
    bove
    0.55
    TagHelpers
    0.54
    hypothesis
    0.53
    Activations Density 3.192%

    No Known Activations