© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9042
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to travel plans and travel destinations

    oai_token-act-pair · gemini-2.0-flash

    forms of the word 'transfer'

    np_token-act-pair-logits · gpt-4o-mini

    transfer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    MLLoader
    -0.76
    contentLoaded
    -0.70
    AccessorTable
    -0.67
    Personendaten
    -0.66
    AnchorTagHelper
    -0.63
     ivelany
    -0.63
     Roskov
    -0.61
     fubject
    -0.60
    RegressionTest
    -0.59
    MigrationBuilder
    -0.58
    POSITIVE LOGITS
     transfer
    0.84
     transfers
    0.84
     Transfers
    0.83
     Transfer
    0.79
    transfer
    0.79
    Transfer
    0.79
    Transfers
    0.72
    transfers
    0.72
     transferred
    0.69
     TRANSFER
    0.68
    Activations Density 1.690%

    No Known Activations