© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13135
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to politics, elections, or current affairs

    oai_token-act-pair · gemini-2.0-flash

    winning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    aarrggbb
    -0.45
     recientemente
    -0.44
    最近
    -0.42
    ništ
    -0.41
    [
    -0.41
    しま
    -0.41
     után
    -0.41
     brazo
    -0.40
    ::
    -0.40
    LEncoder
    -0.40
    POSITIVE LOGITS
     oprot
    0.82
     nakalista
    0.77
    Espèce
    0.72
    EDEFAULT
    0.71
     Reverso
    0.68
     Audiodateien
    0.68
    ParallelGroup
    0.67
    脚注の使い方
    0.66
    SharedDtor
    0.65
    \{\\
    0.64
    Activations Density 36.268%

    No Known Activations