© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7062
    Prev
    Next
    INDEX
    Explanations

    uses of the substring "to say" and a handful of other possibly unrelated words

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -1.16
     שוליים
    -0.71
    aarrggbb
    -0.64
     poveznice
    -0.64
    bootstrapcdn
    -0.60
    Seems
    -0.59
     someone
    -0.57
     whoever
    -0.57
     somebody
    -0.56
    latego
    -0.55
    POSITIVE LOGITS
    complexType
    0.66
     artikkelen
    0.54
    EndContext
    0.54
    modb
    0.52
    NegativeButton
    0.51
     ongles
    0.50
    itude
    0.50
     Kraj
    0.50
    Datuak
    0.50
    ANCIA
    0.50
    Activations Density 1.173%

    No Known Activations