© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1832
    Prev
    Next
    INDEX
    Explanations

    words related to magic, fantasy, mythology, and the supernatural

    oai_token-act-pair · gemini-2.0-flash

    magic

    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
     magic
    -0.71
    IVEREF
    -0.68
     magical
    -0.62
     magie
    -0.59
    magic
    -0.59
     magia
    -0.59
     magique
    -0.57
    Magic
    -0.55
     mágica
    -0.55
     MAGIC
    -0.54
    POSITIVE LOGITS
    المراجع
    0.75
    Datuak
    0.69
     trajets
    0.64
    igshid
    0.64
    ferential
    0.63
    FXMLLoader
    0.62
     poveznice
    0.59
    BindingResult
    0.58
    <bos>
    0.57
    новништво
    0.57
    Activations Density 25.159%

    No Known Activations