© 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. 2006
    Prev
    Next
    INDEX
    Explanations

    code and associated messaging

    oai_token-act-pair · gemini-2.0-flash

    request

    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
     StatefulWidget
    -0.62
    #
    -0.61
    XmlAccessType
    -0.60
    setVerticalGroup
    -0.56
     Neve
    -0.54
     Schar
    -0.54
    $_['
    -0.53
     whip
    -0.53
    fieldId
    -0.53
     noDo
    -0.53
    POSITIVE LOGITS
     CSM
    0.47
    Становништво
    0.47
     insuffisamment
    0.47
    bbene
    0.45
     getUsername
    0.45
     auguri
    0.44
     slutt
    0.43
     suom
    0.43
     myö
    0.43
     täh
    0.43
    Activations Density 4.822%

    No Known Activations