© 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. 14164
    Prev
    Next
    INDEX
    Explanations

    references to legal concepts, especially related to the US Constitution and First Amendment rights

    oai_token-act-pair · gemini-2.0-flash

    rights and amendments

    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
    poy
    -0.57
    τας
    -0.44
    teira
    -0.44
    ound
    -0.44
    ook
    -0.44
    esistenza
    -0.43
    pyr
    -0.42
     Bes
    -0.42
    ExecutionContext
    -0.41
    nack
    -0.41
    POSITIVE LOGITS
     الحره
    0.59
    ()].
    0.58
    modelBuilder
    0.58
    parsedMessage
    0.57
    UrlResolution
    0.57
    AddTagHelper
    0.57
    ThroughAttribute
    0.57
    ReusableCell
    0.55
     Wikimédia
    0.54
     gyhoeddwyd
    0.54
    Activations Density 3.465%

    No Known Activations