© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12769
    Prev
    Next
    INDEX
    Explanations

    the word "selected"

    oai_token-act-pair · gemini-2.0-flash

    selected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     selected
    -2.13
    selected
    -1.88
     Selected
    -1.86
    Selected
    -1.78
     chosen
    -1.66
     SELECTED
    -1.48
     ausgewä
    -1.39
    chosen
    -1.34
     выбран
    -1.29
    SELECTED
    -1.27
    POSITIVE LOGITS
    awn
    0.48
    wide
    0.47
     wide
    0.44
    殻
    0.42
     onAnimation
    0.42
    летний
    0.40
     broad
    0.40
     appels
    0.40
    inas
    0.39
    0.39
    Activations Density 1.287%

    No Known Activations