© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10905
    Prev
    Next
    INDEX
    Explanations

    code snippets related to JavaScript property deletion

    oai_token-act-pair · gemini-2.0-flash

    Deleting files, properties

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     removal
    -2.42
     Removal
    -2.33
     elimination
    -2.17
    Removal
    -2.13
     removed
    -2.09
     Removing
    -2.08
    removal
    -2.08
     removing
    -2.08
     remove
    -2.03
    Removing
    -1.98
    POSITIVE LOGITS
    BagConstraints
    0.60
     linkovi
    0.59
     estimés
    0.58
    bilt
    0.46
    BeginInit
    0.46
    ramientas
    0.45
     gynhyrchwyd
    0.44
     تجمعات
    0.43
    hidupan
    0.42
    entary
    0.42
    Activations Density 2.335%

    No Known Activations