© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6588
    Prev
    Next
    INDEX
    Explanations

    the word "Sigmund" or words associated with audio software, particularly delays and effects, in the context of macOS

    oai_token-act-pair · gemini-2.0-flash

    non-English vocabulary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    play
    -0.54
    PhysRevLett
    -0.50
    cplusplus
    -0.46
     przys
    -0.44
    Play
    -0.44
     plays
    -0.44
    Fitz
    -0.43
    zension
    -0.43
     Fitz
    -0.42
    Stream
    -0.42
    POSITIVE LOGITS
    脚注の使い方
    0.69
     متعلقه
    0.67
    XmlAccessType
    0.65
    GOTREF
    0.61
    AccessorTable
    0.61
     שוליים
    0.61
    SharedCtor
    0.60
    PMailer
    0.60
    הערות
    0.60
    utilisons
    0.58
    Activations Density 1.565%

    No Known Activations