© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9152
    Prev
    Next
    INDEX
    Explanations

    words related to taking action to learn about something or change things

    oai_token-act-pair · gemini-2.0-flash

    actions or advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ViewFeatures
    -0.99
    oredCriteria
    -0.83
    parsedMessage
    -0.75
     Мексичка
    -0.74
     Paglinawan
    -0.73
    IsContent
    -0.71
     &___
    -0.70
    addCriterion
    -0.66
    AndPassword
    -0.66
     мәкал
    -0.66
    POSITIVE LOGITS
    .
    0.48
     BioLib
    0.46
    ineno
    0.40
    msgSender
    0.40
    Leben
    0.40
    tott
    0.38
    MUM
    0.38
    unhofer
    0.38
     والث
    0.37
     conformation
    0.37
    Activations Density 1.375%

    No Known Activations