© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4001
    Prev
    Next
    INDEX
    Explanations

    words related to diagrams and stability, possibly within a scientific context involving some kind of market or physical system

    oai_token-act-pair · gemini-2.0-flash

    bifurcation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    -0.63
    verwijspagina
    -0.59
    featureID
    -0.56
    <bos>
    -0.56
     Gerv
    -0.49
     linkovi
    -0.49
     Bucket
    -0.47
    fieldId
    -0.46
    StartCoroutine
    -0.46
    jsonwebtoken
    -0.46
    POSITIVE LOGITS
     présidenti
    0.63
    signee
    0.56
     lược
    0.55
     وتسجيلات
    0.54
     hornear
    0.54
    unton
    0.52
    ORAGE
    0.51
     allant
    0.50
     militaires
    0.50
     quæ
    0.50
    Activations Density 5.072%

    No Known Activations