© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4937
    Prev
    Next
    INDEX
    Explanations

    the word "peer" and in some instances, the letter R

    oai_token-act-pair · gemini-2.0-flash

    peer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     I
    -0.84
     (
    -0.77
     
    -0.75
     de
    -0.75
    AddTagHelper
    -0.74
     F
    -0.73
    ↵↵
    -0.73
     E
    -0.72
     But
    -0.72
     H
    -0.71
    POSITIVE LOGITS
     piú
    1.51
     ainfi
    1.50
     avoient
    1.48
     feroit
    1.47
     auroit
    1.45
     étoit
    1.38
     étoient
    1.36
     Jefus
    1.34
     enfans
    1.34
     tasche
    1.32
    Activations Density 4.087%

    No Known Activations