© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10667
    Prev
    Next
    INDEX
    Explanations

    references to mythology, fantasy, or sci-fi.

    oai_token-act-pair · gemini-2.0-flash

    Monsters and villains

    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
    SequentialGroup
    -0.84
     nakalista
    -0.58
    Personendaten
    -0.57
    bua
    -0.56
    anique
    -0.54
    rima
    -0.54
    telser
    -0.54
    isContained
    -0.54
    orElseThrow
    -0.54
    boné
    -0.53
    POSITIVE LOGITS
     ExecuteAsync
    0.71
     eventdata
    0.59
     AssemblyTitle
    0.55
    出版年
    0.54
     Akismet
    0.50
     ModelExpression
    0.50
     linkovi
    0.49
    CodeAttribute
    0.47
     Bluestacks
    0.47
    IndentedString
    0.46
    Activations Density 3.608%

    No Known Activations