© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6612
    Prev
    Next
    INDEX
    Explanations

    phrases involving prepositions like "to", "for," or "in" combined with a verb.

    oai_token-act-pair · gemini-2.0-flash

    compensate

    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
     Paglinawan
    -0.92
    contentLoaded
    -0.78
    Хьажоргаш
    -0.71
    VolleyError
    -0.63
     ProtoMessage
    -0.61
    writeFieldEnd
    -0.60
     ddelweddau
    -0.59
    ItemBackground
    -0.58
     चीज़ों
    -0.57
     Meksiku
    -0.56
    POSITIVE LOGITS
     compens
    1.84
     compensate
    1.81
     compensated
    1.80
     compensation
    1.79
    compens
    1.78
     Compens
    1.75
     compensating
    1.71
     Compensation
    1.64
    compensation
    1.63
    Compensation
    1.55
    Activations Density 1.345%

    No Known Activations