© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11367
    Prev
    Next
    INDEX
    Explanations

    words associated with planning to do something

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    +#+#
    -0.54
    WithEmail
    -0.51
     cristiano
    -0.46
     Çünkü
    -0.45
     poupée
    -0.43
    Sucesor
    -0.43
     cref
    -0.43
     cristianos
    -0.43
     Américas
    -0.42
     Tode
    -0.42
    POSITIVE LOGITS
    Odkazy
    0.77
    ترنت
    0.68
     linkovi
    0.65
    bootstrapcdn
    0.65
    Bronnen
    0.64
    ANSA
    0.63
    rawDesc
    0.62
    AccessorTable
    0.59
     esternos
    0.59
    Referensi
    0.59
    Activations Density 7.040%

    No Known Activations