© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16175
    Prev
    Next
    INDEX
    Explanations

    clauses with commas and words related to time, events and controversies

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    HasForeignKey
    -0.68
    UserScript
    -0.62
    XmlAccessType
    -0.60
    BagConstraints
    -0.54
    uitton
    -0.54
     pinulongan
    -0.53
    saraba
    -0.52
    leby
    -0.52
    OrNil
    -0.50
    InSection
    -0.48
    POSITIVE LOGITS
     with
    1.63
    with
    1.25
     avec
    1.23
     WITH
    1.12
     With
    1.09
     với
    1.09
     dengan
    1.08
    With
    1.07
    avec
    1.03
    WITH
    0.92
    Activations Density 1.420%

    No Known Activations