© 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. 12982
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

    oai_token-act-pair · gemini-2.0-flash

    for

    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
     estabiliz
    -0.52
     rangs
    -0.51
     detalj
    -0.46
     framför
    -0.45
     demais
    -0.45
     terhadap
    -0.43
     pantaloni
    -0.43
     richten
    -0.43
     giacca
    -0.43
     linkovi
    -0.43
    POSITIVE LOGITS
     betweenstory
    0.73
     killing
    0.68
     getting
    0.68
     registering
    0.66
     Reverso
    0.65
    ьаж
    0.63
     us
    0.63
    windowFixed
    0.63
     creating
    0.62
    parsedMessage
    0.62
    Activations Density 19.204%

    No Known Activations