© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13827
    Prev
    Next
    INDEX
    Explanations

    the word "invite" and also has a weaker matching on the word "offer", and "called" and "guests"

    oai_token-act-pair · gemini-2.0-flash

    invite

    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
    Negative Logits
    <bos>
    -0.87
     entre
    -0.85
     kasarigan
    -0.71
    entre
    -0.56
    insics
    -0.55
     start
    -0.51
     noqa
    -0.51
    outState
    -0.50
     transférez
    -0.50
    OptionsMenu
    -0.50
    POSITIVE LOGITS
    󠁢
    0.68
    TintMode
    0.61
     réguli
    0.60
     textStatus
    0.58
     considérons
    0.58
     hidrá
    0.57
     }}"></
    0.57
    eradish
    0.57
     vägen
    0.57
    ="#"><
    0.56
    Activations Density 0.514%

    No Known Activations