© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1576
    Prev
    Next
    INDEX
    Explanations

    prepositions and auxiliary verbs in the context of a business transaction

    oai_token-act-pair · gemini-2.0-flash

    prepositions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     refusé
    -0.80
     abbia
    -0.63
     détru
    -0.62
     disparu
    -0.61
    propagate
    -0.60
    ^(@)
    -0.60
     répondu
    -0.59
    >');
    -0.58
     stabilize
    -0.57
     montré
    -0.57
    POSITIVE LOGITS
     being
    1.05
     making
    0.93
     giving
    0.91
     having
    0.88
     taking
    0.87
     appearing
    0.86
     creating
    0.82
     becoming
    0.82
     forming
    0.82
     getting
    0.81
    Activations Density 2.786%

    No Known Activations