© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7956
    Prev
    Next
    INDEX
    Explanations

    the word "tool"

    oai_token-act-pair · gemini-2.0-flash

    tool

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ,
    -0.84
    .
    -0.79
    -
    -0.77
     A
    -0.73
     a
    -0.71
     (
    -0.71
    ;
    -0.68
     in
    -0.68
     I
    -0.67
    :
    -0.66
    POSITIVE LOGITS
     itſelf
    1.45
     myſelf
    1.38
     iſt
    1.27
     Houſe
    1.22
     Efq
    1.18
     Monfieur
    1.16
     ―――――
    1.15
     doubtnut
    1.13
     ་་
    1.13
    ſelves
    1.12
    Activations Density 0.830%

    No Known Activations