© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4002
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to family history and land ownership.

    oai_token-act-pair · gemini-2.0-flash

    Land ownership and farms

    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
    Atsauces
    -0.53
    nościo
    -0.48
    awtextra
    -0.47
     Farms
    -0.46
     Control
    -0.46
    Control
    -0.44
    Referencie
    -0.44
     control
    -0.44
    ArgsConstructor
    -0.43
    jstor
    -0.43
    POSITIVE LOGITS
    ammans
    0.64
     estimés
    0.63
     Meksiku
    0.61
    ioare
    0.57
    міністра
    0.56
    EndGlobalSection
    0.55
    Clik
    0.55
    hdysval
    0.54
     land
    0.53
     ویکی‌پدی
    0.53
    Activations Density 6.556%

    No Known Activations