© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11274
    Prev
    Next
    INDEX
    Explanations

    the word "pretty" and weak associations like "much"

    oai_token-act-pair · gemini-2.0-flash

    pretty

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     pretty
    -1.82
    pretty
    -1.73
    Pretty
    -1.65
     Pretty
    -1.58
     PRET
    -1.21
    PRET
    -0.70
     Fairly
    -0.63
    蠻
    -0.61
    ंदीखरीदारी
    -0.60
     ganska
    -0.59
    POSITIVE LOGITS
    SequentialGroup
    0.62
    jspx
    0.56
    subsubsection
    0.54
    makeConstraints
    0.54
    InputTagHelper
    0.51
    mappedBy
    0.50
    UnknownFieldSet
    0.50
    lands
    0.50
    uminense
    0.49
    FormTagHelper
    0.49
    Activations Density 2.851%

    No Known Activations