© 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. 8796
    Prev
    Next
    INDEX
    Explanations

    seemingly unrelated topics, but with an overlap of acronyms, numbers and chemical or scientific terminology.

    oai_token-act-pair · 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
    principalColumn
    -0.58
    ALAM
    -0.52
    tase
    -0.47
     архивлан
    -0.45
    ties
    -0.44
    EMAS
    -0.44
    دانشنامهٔ
    -0.43
     insegna
    -0.42
     oignons
    -0.42
    tius
    -0.42
    POSITIVE LOGITS
    featureID
    0.78
     utafitiHapana
    0.69
     فريبيس
    0.67
    ArgumentParser
    0.66
    rungsseite
    0.65
    apimachinery
    0.63
    endphp
    0.61
     CanadaChoose
    0.61
    DockStyle
    0.58
    inander
    0.54
    Activations Density 2.194%

    No Known Activations