© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14415
    Prev
    Next
    INDEX
    Explanations

    the letter J, specifically following a name like Michal or modifying a word joint

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    AccessorTable
    -1.32
     myſelf
    -1.31
     itſelf
    -1.09
     purpoſe
    -1.09
    AndEndTag
    -1.09
     AssemblyCulture
    -1.09
     Monfieur
    -1.07
     pleaſure
    -1.05
     themſelves
    -1.03
    ArrowToggle
    -1.03
    POSITIVE LOGITS
     a
    0.44
    ,
    0.35
    c
    0.31
     and
    0.29
    vm
    0.28
    pisah
    0.28
     R
    0.28
    <eos>
    0.28
     (
    0.27
    mocha
    0.26
    Activations Density 0.123%

    No Known Activations