© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10683
    Prev
    Next
    INDEX
    Explanations

    phrases about Russia's interactions with other countries

    oai_token-act-pair · gemini-2.0-flash

    Russia/Ukraine/Norway

    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
     Monfieur
    -0.74
     surla
    -0.72
    AccessorTable
    -0.71
     Efq
    -0.69
     itſelf
    -0.69
     purpoſe
    -0.68
     juſt
    -0.67
     kasarigan
    -0.66
    ThroughAttribute
    -0.66
     Reſ
    -0.66
    POSITIVE LOGITS
     f
    0.51
    <eos>
    0.50
    irah
    0.48
    <bos>
    0.47
    rospy
    0.47
     jadi
    0.46
    principalTable
    0.46
     um
    0.46
    울
    0.45
     Co
    0.45
    Activations Density 14.802%

    No Known Activations