© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15886
    Prev
    Next
    INDEX
    Explanations

    uses of the word "with" preceding words and phrases related to collaboration, cooperation, or tool use

    oai_token-act-pair · gemini-2.0-flash

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     kiệm
    -0.61
    MigrationBuilder
    -0.60
     travaillons
    -0.58
     estekak
    -0.57
     femininas
    -0.56
     fallu
    -0.56
     âgées
    -0.56
    guien
    -0.56
    ErrUnexpectedEOF
    -0.56
    Demografia
    -0.55
    POSITIVE LOGITS
     a
    0.71
     the
    0.69
     lots
    0.68
     an
    0.59
    onova
    0.56
     ControllerBase
    0.54
    onNext
    0.53
    eeq
    0.52
    θεν
    0.50
     us
    0.50
    Activations Density 18.961%

    No Known Activations