© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14444
    Prev
    Next
    INDEX
    Explanations

    mentions of Russian interference in US politics and the investigation into it.

    oai_token-act-pair · gemini-2.0-flash

    Russian

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Russian
    -1.34
     Russia
    -1.27
    Russian
    -1.23
     RUSS
    -1.11
    Russia
    -1.10
     Russland
    -1.07
     Rusia
    -1.07
     Russians
    -1.05
     russian
    -0.99
     russes
    -0.99
    POSITIVE LOGITS
    AnchorStyles
    0.53
    lgari
    0.48
    useState
    0.48
    utsal
    0.47
    -------
    0.47
    oredCriteria
    0.46
    धार
    0.45
     Owens
    0.44
     ax
    0.44
     Украи
    0.44
    Activations Density 1.740%

    No Known Activations