© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3383
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to predicting the future or dealing with long-term strategies

    oai_token-act-pair · gemini-2.0-flash

    future predictions/business

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     autorytatywna
    -0.69
     AssemblyProduct
    -0.69
    migrationBuilder
    -0.69
    expandindo
    -0.68
    Personensuche
    -0.65
    Personendaten
    -0.65
     المعيارى
    -0.63
    IsContent
    -0.60
    ImageContext
    -0.60
    :+:
    -0.60
    POSITIVE LOGITS
     future
    0.76
     Future
    0.69
    Future
    0.68
    FUTURE
    0.65
    future
    0.65
     FUTURE
    0.58
     futuro
    0.54
    未来
    0.53
     futuras
    0.51
     avenir
    0.50
    Activations Density 1.871%

    No Known Activations