© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14085
    Prev
    Next
    INDEX
    Explanations

    mixed negative sentiments and strong assertions in argumentative contexts.

    oai_token-act-pair · gemini-2.0-flash

    opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     ermittelt
    -0.46
    I
    -0.45
     traditionnels
    -0.44
     Lacy
    -0.43
     față
    -0.43
     någon
    -0.41
     esetén
    -0.41
     lumea
    -0.40
     Slovensku
    -0.40
    kesmas
    -0.39
    POSITIVE LOGITS
     newBuilder
    0.85
    httphttps
    0.82
     @"/
    0.71
    WireFormatLite
    0.69
     Svar
    0.69
    MessageOf
    0.67
     مشين
    0.67
    ̀
    0.67
    hasMoreElements
    0.66
    WebVitals
    0.65
    Activations Density 2.346%

    No Known Activations