© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10452
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessive adjectives

    oai_token-act-pair · gemini-2.0-flash

    Code/Markup segments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     AssemblyCulture
    -0.62
    setVerticalGroup
    -0.55
     considérons
    -0.52
     alman
    -0.49
    versaries
    -0.48
    StateList
    -0.48
     Aras
    -0.47
     Hypers
    -0.47
     ELF
    -0.47
    Expedia
    -0.47
    POSITIVE LOGITS
    <bos>
    0.88
     avoient
    0.66
    präsident
    0.64
     Monfieur
    0.64
     our
    0.60
     AssemblyTitle
    0.60
     chofe
    0.59
    lardır
    0.58
    TagMode
    0.58
     AssemblyVersion
    0.57
    Activations Density 5.750%

    No Known Activations