© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10598
    Prev
    Next
    INDEX
    Explanations

    the US and Russia and their relationship to each other

    oai_token-act-pair · gemini-2.0-flash

    Russian names/places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     mxArray
    -0.63
    Datuak
    -0.59
     TextAppearance
    -0.57
     Jones
    -0.52
     protoimpl
    -0.52
     Hicks
    -0.52
    AccessorTable
    -0.50
     Hughes
    -0.50
    Parcelize
    -0.50
     Hudson
    -0.49
    POSITIVE LOGITS
     Vasili
    0.74
     Novgorod
    0.74
     Kremlin
    0.73
     Vlas
    0.72
     rubles
    0.71
     Viktor
    0.71
     Leningrad
    0.70
     Soviets
    0.70
     Lenin
    0.69
     Pushkin
    0.69
    Activations Density 53.515%

    No Known Activations