© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5036
    Prev
    Next
    INDEX
    Explanations

    quotes and political statements related to Malaysian politics

    oai_token-act-pair · gemini-2.0-flash

    Malaysian politics

    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
     InputDecoration
    -0.42
    IconModule
    -0.40
    __':
    -0.39
     lenker
    -0.38
     About
    -0.38
    KommentareTeilen
    -0.37
    ResumeLayout
    -0.37
     pourriez
    -0.36
     off
    -0.36
    of
    -0.35
    POSITIVE LOGITS
     utafitiHapana
    0.77
    IContainer
    0.75
    kháu
    0.73
     يتيمه
    0.73
     ſeveral
    0.72
     theſe
    0.72
    HasBeenSet
    0.71
    sivity
    0.71
    AnimationsModule
    0.68
     itſelf
    0.68
    Activations Density 19.271%

    No Known Activations