© 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. 247
    Prev
    Next
    INDEX
    Explanations

    lines of code defining the `get` and `set` methods of a property

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
     disponibilités
    -0.94
     Monfieur
    -0.89
    #+#
    -0.86
    CppMethod
    -0.83
     scolaires
    -0.79
     propOrder
    -0.79
    はじめに
    -0.78
     sanitaires
    -0.77
    parsedMessage
    -0.77
     виправивши
    -0.77
    POSITIVE LOGITS
    NameInMap
    0.50
     la
    0.43
    APORE
    0.41
    featureID
    0.39
    kn
    0.38
    -
    0.38
    astify
    0.35
    UserScript
    0.35
     Abgerufen
    0.35
     rep
    0.35
    Activations Density 0.543%

    No Known Activations