© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8551
    Prev
    Next
    INDEX
    Explanations

    words related to data analysis and interpretation

    oai_token-act-pair · gemini-2.0-flash

    French words starting with specific characters

    np_token-act-pair-logits · gpt-4o-mini

    French words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ones
    -0.90
     Ones
    -0.69
    IndentedString
    -0.67
    ophan
    -0.65
    ')")
    -0.64
    %"),
    -0.63
    %?
    -0.62
     himo
    -0.62
     patin
    -0.61
    Rptr
    -0.60
    POSITIVE LOGITS
     vérit
    0.80
     nuages
    0.78
     démocr
    0.77
     oreilles
    0.75
     blessés
    0.75
     commerciales
    0.74
     ouvriers
    0.73
     épaules
    0.73
     doigts
    0.71
     genoux
    0.70
    Activations Density 17.354%

    No Known Activations