© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12561
    Prev
    Next
    INDEX
    Explanations

    words related to political processes, especially around the creation and approval of legislation

    oai_token-act-pair · gemini-2.0-flash

    News and political actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     محفوظة
    -0.59
    RetentionPolicy
    -0.59
    קישורים
    -0.55
     friable
    -0.53
     själ
    -0.52
    łasz
    -0.52
     democrática
    -0.51
    ագրություններ
    -0.49
     refraction
    -0.49
    atet
    -0.49
    POSITIVE LOGITS
    StructEnd
    0.73
    ScopeManager
    0.61
    typeorm
    0.57
    queryInterface
    0.57
     Roskov
    0.54
     draw
    0.54
    AndroidJUnit
    0.54
    ۜ
    0.52
    richTextPanel
    0.49
     transfieras
    0.49
    Activations Density 2.075%

    No Known Activations