© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4934
    Prev
    Next
    INDEX
    Explanations

    the word "relax" (as well as words related to that concept)

    oai_token-act-pair · gemini-2.0-flash

    relax

    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
    itisation
    -0.89
    endphp
    -0.89
    <bos>
    -0.85
    alised
    -0.79
    =$?
    -0.79
    favourites
    -0.78
    eavour
    -0.77
    umably
    -0.77
    ourites
    -0.75
    RenderAtEndOf
    -0.74
    POSITIVE LOGITS
     picioare
    1.00
     creș
    0.93
     argint
    0.73
     nicio
    0.68
     față
    0.67
     maș
    0.66
     oamen
    0.65
     deveria
    0.65
     morrer
    0.65
     piele
    0.63
    Activations Density 1.943%

    No Known Activations