© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10113
    Prev
    Next
    INDEX
    Explanations

    vocabulary related to the chemical conversion of hydrocarbons

    oai_token-act-pair · gemini-2.0-flash

    range

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     esternos
    -0.50
    ysa
    -0.48
    PUBLIC
    -0.48
    łosi
    -0.48
    svet
    -0.47
    ocin
    -0.46
     *)__
    -0.46
     Madi
    -0.46
     trị
    -0.46
     stupidity
    -0.46
    POSITIVE LOGITS
     nakalista
    0.75
    évaluateur
    0.66
    TagMode
    0.66
    AndEndTag
    0.65
     kasarigan
    0.64
    ValueStyle
    0.61
     CreateTagHelper
    0.61
     EconPapers
    0.60
    ANTLR
    0.60
     >=",
    0.60
    Activations Density 1.690%

    No Known Activations