© 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. 9887
    Prev
    Next
    INDEX
    Explanations

    the string "car" when it isn't part of the word "because"

    oai_token-act-pair · gemini-2.0-flash

    car

    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
     car
    -2.81
     Car
    -2.42
    Car
    -2.38
    car
    -2.31
     CAR
    -1.77
     cars
    -1.73
    CAR
    -1.68
    cars
    -1.56
    Cars
    -1.47
     Cars
    -1.43
    POSITIVE LOGITS
    OrBuilder
    0.80
     nakalista
    0.71
    TypedDataSet
    0.71
    migrationBuilder
    0.67
     snippetHide
    0.65
    IBOutlet
    0.65
     getPassword
    0.64
    abestanden
    0.64
    KURZBESCHREIBUNG
    0.63
    SharedDtor
    0.63
    Activations Density 2.251%

    No Known Activations