© 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. 9611
    Prev
    Next
    INDEX
    Explanations

    a mix of strong opinions and names/identifiers that could be associated with people.

    oai_token-act-pair · gemini-2.0-flash

    sensitive discussions

    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
    rxjs
    -0.61
    VIAF
    -0.48
     يول
    -0.48
    hpur
    -0.47
    openqa
    -0.47
     endroit
    -0.46
    KeySpec
    -0.46
     AppBar
    -0.45
     turística
    -0.45
    quitous
    -0.45
    POSITIVE LOGITS
     initWithFrame
    0.58
    AccessorTable
    0.57
    sendRedirect
    0.57
     referenties
    0.56
     localVar
    0.56
    uyasha
    0.55
    Personendaten
    0.54
     Réponses
    0.53
    ginal
    0.51
    -@
    0.50
    Activations Density 1.471%

    No Known Activations