© 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. 4180
    Prev
    Next
    INDEX
    Explanations

    words about politics, particularly related to power struggles involving tribes and political figures.

    oai_token-act-pair · gemini-2.0-flash

    power

    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
     typelib
    -0.76
     Вікі
    -0.70
    enumii
    -0.68
    VersionUID
    -0.68
    GraphicsUnit
    -0.68
    зулта
    -0.65
    )}</
    -0.64
    })*/
    -0.63
     initComponents
    -0.62
    InvalidProtocol
    -0.62
    POSITIVE LOGITS
     power
    1.34
    power
    1.15
     Power
    1.05
    Power
    1.03
     POWER
    0.94
    POWER
    0.89
     balance
    0.88
    パワー
    0.82
    balance
    0.77
     poder
    0.75
    Activations Density 2.502%

    No Known Activations