© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10891
    Prev
    Next
    INDEX
    Explanations

    words related to organic chemistry, especially "ortho" and "para" positions

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     para
    -1.85
    Para
    -1.68
     Para
    -1.63
     PARA
    -1.48
    para
    -1.46
    PARA
    -1.24
     pentru
    -0.73
     pour
    -0.71
     por
    -0.69
    pour
    -0.60
    POSITIVE LOGITS
     ISNI
    0.62
     ver
    0.59
     ve
    0.52
     Verfügung
    0.49
    ResumeLayout
    0.49
     verle
    0.49
    ėk
    0.49
    veel
    0.48
    TypedDataSet
    0.47
    цо
    0.46
    Activations Density 0.783%

    No Known Activations