© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 8433
    Prev
    Next
    INDEX
    Explanations

    measurements and verbs that end in "ing" or mention measurements in scientific contexts.

    oai_token-act-pair · gemini-2.0-flash

    process descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     tear
    -0.68
     tears
    -0.58
    codile
    -0.57
     Baillargeon
    -0.56
    yntaxException
    -0.53
     Tear
    -0.51
     Mies
    -0.50
     MenuView
    -0.50
     Isk
    -0.50
    niosek
    -0.50
    POSITIVE LOGITS
    expandindo
    0.66
    তথ্যসূত্র
    0.60
    èlement
    0.59
     Infórmanos
    0.57
    boru
    0.54
     Aja
    0.53
    vény
    0.53
     autorytatywna
    0.52
     Zufall
    0.52
    Carriera
    0.52
    Activations Density 1.207%

    No Known Activations