© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 31
    Prev
    Next
    INDEX
    Explanations

    the word "Car" followed by a variable number of other letters

    oai_token-act-pair · gemini-2.0-flash

    Car

    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
     car
    -0.64
     hObject
    -0.60
    CAR
    -0.60
    Car
    -0.55
     Car
    -0.54
    car
    -0.54
     InputDecoration
    -0.50
     EconPapers
    -0.50
     <",
    -0.48
     CAR
    -0.48
    POSITIVE LOGITS
    ranger
    0.54
    imarães
    0.54
    reras
    0.53
    vajal
    0.53
    rister
    0.52
     consultato
    0.52
    rillo
    0.51
    penters
    0.51
    tagena
    0.51
    reira
    0.51
    Activations Density 3.975%

    No Known Activations