© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8591
    Prev
    Next
    INDEX
    Explanations

    expressions used to acknowledge, thank or express gratitude to individuals or organizations

    oai_token-act-pair · gemini-2.0-flash

    say "to"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     willing
    -0.71
     Willing
    -0.63
     refuses
    -0.61
    willing
    -0.60
     Ho
    -0.59
     habit
    -0.58
     unwilling
    -0.58
     newOwner
    -0.57
    Willing
    -0.57
     Sch
    -0.56
    POSITIVE LOGITS
     للمعارف
    0.82
     disambiguazione
    0.81
     myſelf
    0.71
     ſta
    0.70
     ſtate
    0.69
     anſ
    0.68
     deſt
    0.68
     againſt
    0.67
     juſ
    0.66
     Efq
    0.66
    Activations Density 1.160%

    No Known Activations