© 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. 4111
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and punctuation indicating questions or uncertainty

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    ThroughAttribute
    -0.62
    GraphicsUnit
    -0.57
     "..\..\
    -0.56
     >=",
    -0.56
    Tikang
    -0.55
     trust
    -0.53
    NameInMap
    -0.52
    RegressionTest
    -0.50
     Soro
    -0.48
     trusts
    -0.48
    POSITIVE LOGITS
     May
    0.65
    May
    0.60
    arXiv
    0.55
    cookieParser
    0.54
    createCanvas
    0.52
     Most
    0.51
    出版年
    0.51
     may
    0.51
     Might
    0.51
    Может
    0.51
    Activations Density 2.175%

    No Known Activations