© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11129
    Prev
    Next
    INDEX
    Explanations

    uses of articles, prepositions and numbers, particularly "a," "of," "in","an", "the", "one", "to", "at", "by", and single digits

    oai_token-act-pair · gemini-2.0-flash

    darkness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     bonté
    -0.56
     victimes
    -0.54
    ofern
    -0.49
     referenties
    -0.49
     gespielt
    -0.48
     geschafft
    -0.47
    __*/
    -0.47
     tiket
    -0.47
     moeite
    -0.47
     előtt
    -0.46
    POSITIVE LOGITS
     dark
    1.46
    dark
    1.22
     grim
    1.18
     darkest
    1.13
     gris
    1.11
     darker
    1.05
     bleak
    1.03
     DARK
    1.03
     Dark
    1.01
    Dark
    0.97
    Activations Density 3.789%

    No Known Activations