© 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. 3186
    Prev
    Next
    INDEX
    Explanations

    the phrase "sort of". Its activation drops when the word following "of" has higher information content

    oai_token-act-pair · gemini-2.0-flash

    sort

    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
     part
    -0.58
    部分
    -0.56
    <bos>
    -0.54
    Partial
    -0.54
     部分
    -0.53
     partial
    -0.52
     parte
    -0.50
     partially
    -0.49
     parts
    -0.48
     Partial
    -0.45
    POSITIVE LOGITS
    IsContent
    0.82
    ConstraintMaker
    0.80
     "..\..\..\
    0.80
     nakalista
    0.80
    MigrationBuilder
    0.77
    Rhestr
    0.75
    IntoConstraints
    0.75
     geslacht
    0.74
    PhysRev
    0.73
     Combien
    0.73
    Activations Density 1.242%

    No Known Activations