© 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. 8587
    Prev
    Next
    INDEX
    Explanations

    details about classic cars, particularly muscle cars from the late 1960s and early 1970s.

    oai_token-act-pair · gemini-2.0-flash

    cars and car manufacturing

    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
    Personendaten
    -0.66
    WebVitals
    -0.64
    MIDDLEWARE
    -0.57
     GenerationType
    -0.54
     car
    -0.54
    awtextra
    -0.54
    ArgsConstructor
    -0.53
    ImageContext
    -0.52
    CompleteListener
    -0.52
    ',
    -0.52
    POSITIVE LOGITS
    OfBirth
    0.53
    HtmlAttribute
    0.49
     getContext
    0.48
    原始内容存档于
    0.48
    ihnachten
    0.47
    ByDefault
    0.46
    envolvimento
    0.45
    withOpacity
    0.44
    ību
    0.44
    ības
    0.44
    Activations Density 2.974%

    No Known Activations