© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11345
    Prev
    Next
    INDEX
    Explanations

    words and phrases that express comparisons, change, and future possibility

    oai_token-act-pair · gemini-2.0-flash

    number

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     coû
    -0.57
     mondi
    -0.53
     popoli
    -0.51
     sicura
    -0.50
     piú
    -0.49
    AccessorTable
    -0.49
     rağmen
    -0.48
     médicaux
    -0.47
     rempliss
    -0.47
     morire
    -0.47
    POSITIVE LOGITS
     number
    0.83
     Number
    0.69
    number
    0.68
     número
    0.68
     numero
    0.66
    Number
    0.66
     Numero
    0.66
     the
    0.66
     NUMBER
    0.65
     insuffisamment
    0.63
    Activations Density 6.921%

    No Known Activations