© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6711
    Prev
    Next
    INDEX
    Explanations

    references to body parts and emotional reactions

    oai_token-act-pair · gemini-2.0-flash

    Descriptions of a person

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     Conſ
    -0.66
     greateſt
    -0.58
     pleaſure
    -0.57
     consultative
    -0.56
    =""></
    -0.56
     quæ
    -0.56
     Chriftian
    -0.56
    RegressionTest
    -0.55
     للاسماء
    -0.55
     becauſe
    -0.54
    POSITIVE LOGITS
    wahati
    0.57
     становника
    0.54
     كمان
    0.51
     للمعارف
    0.48
    Билгалдахарш
    0.46
    LayoutPanel
    0.45
     ItemStack
    0.44
    peh
    0.44
    NUMX
    0.43
    Personen
    0.43
    Activations Density 0.607%

    No Known Activations