© 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. 6142
    Prev
    Next
    INDEX
    Explanations

    text related to the Indian political party BJP

    oai_token-act-pair · gemini-2.0-flash

    political parties and elections

    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
    <tbody>
    -0.56
     movement
    -0.55
     varandra
    -0.55
     TextInputType
    -0.54
     movements
    -0.53
    movement
    -0.53
     esternos
    -0.52
    QApplication
    -0.51
    قایناق‌لار
    -0.51
    Movement
    -0.50
    POSITIVE LOGITS
    RenderAtEndOf
    0.72
     EconPapers
    0.65
     initComponents
    0.57
    @[+][
    0.54
    principalColumn
    0.53
     समीक्षक
    0.52
    EndInit
    0.51
    UnknownFieldSet
    0.50
    AddTagHelper
    0.49
    ądź
    0.49
    Activations Density 0.339%

    No Known Activations