© 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. 10963
    Prev
    Next
    INDEX
    Explanations

    the word "three"

    oai_token-act-pair · gemini-2.0-flash

    three

    np_max-act · gemini-2.0-flash

    three

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    3
    -0.91
     Jefus
    -0.73
    <bos>
    -0.69
     Jurí
    -0.67
     becauſe
    -0.60
     oocytes
    -0.60
     Vergine
    -0.60
     Aene
    -0.58
     Diſ
    -0.58
     Lugano
    -0.58
    POSITIVE LOGITS
    reactstrap
    0.70
    rd
    0.69
     UnityEngine
    0.68
    Kaynakça
    0.65
     (;;
    0.64
     Breen
    0.61
    GIVEREF
    0.60
    simpleType
    0.60
    DrawerToggle
    0.59
     Kr
    0.59
    Activations Density 1.992%

    No Known Activations