© 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. 11776
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

    oai_token-act-pair · 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
    DateTimeField
    -0.50
    ändigt
    -0.46
     geleden
    -0.46
     Whether
    -0.44
    jangkau
    -0.43
    rubin
    -0.43
    Gatt
    -0.42
    atrième
    -0.42
    ={[
    -0.42
    we
    -0.41
    POSITIVE LOGITS
    rungsseite
    0.76
     who
    0.70
    Hochspringen
    0.69
    mobileqq
    0.63
    \{\\
    0.63
     snippetHide
    0.63
     Administrativna
    0.63
     insuffisamment
    0.61
    +#+#
    0.61
     للاسماء
    0.60
    Activations Density 10.133%

    No Known Activations