© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5616
    Prev
    Next
    INDEX
    Explanations

    places where people play some role as a credible source, and how decisions are made

    oai_token-act-pair · gemini-2.0-flash

    Positions of power

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    contentLoaded
    -0.61
     GetEnumerator
    -0.58
     mergeFrom
    -0.57
     onCancelled
    -0.56
     يتيمه
    -0.54
    ftagPool
    -0.54
    hyrchwyd
    -0.52
     balanceOf
    -0.50
    :].
    -0.49
    ValueStyle
    -0.49
    POSITIVE LOGITS
     gana
    0.55
    RequiresApi
    0.55
    RestController
    0.52
    queryInterface
    0.52
    heur
    0.50
    fhir
    0.50
    cutta
    0.49
     légales
    0.47
    eleste
    0.47
    @@@@@
    0.47
    Activations Density 4.833%

    No Known Activations