© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10688
    Prev
    Next
    INDEX
    Explanations

    code or math terminology referring to templates

    oai_token-act-pair · gemini-2.0-flash

    template

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ceo
    -0.65
     ſche
    -0.64
     Gull
    -0.63
     ſtate
    -0.62
     dyd
    -0.62
     purpoſe
    -0.62
    ()")
    -0.62
     Eſ
    -0.61
    teenth
    -0.61
    AMO
    -0.61
    POSITIVE LOGITS
    <bos>
    1.27
     cherchés
    0.62
     we
    0.60
    Personendaten
    0.55
    ’
    0.52
    AddHtmlAttribute
    0.52
    __":
    0.51
     चीज़ों
    0.49
     navegando
    0.49
    دانشنامهٔ
    0.49
    Activations Density 0.915%

    No Known Activations