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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3829
    Prev
    Next
    INDEX
    Explanations

    hedging language related to future plans

    oai_token-act-pair · gemini-2.0-flash

    Future events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     disambiguazione
    -0.99
    CloseOperation
    -0.77
     lenker
    -0.74
    queryInterface
    -0.73
    PerformLayout
    -0.72
    }$​
    -0.71
     endregion
    -0.71
     Trabal
    -0.71
     présidenti
    -0.71
     Works
    -0.71
    POSITIVE LOGITS
     turn
    0.53
     step
    0.49
     enter
    0.43
     consider
    0.43
     import
    0.42
     ra
    0.41
    Y
    0.40
     int
    0.39
     Y
    0.39
     push
    0.39
    Activations Density 2.100%

    No Known Activations