© 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. 12-GEMMASCOPE-TRANSCODER-16K
    4. 13216
    Prev
    Next
    INDEX
    Explanations

    words and short phrases that often appear in technical and scientific documents, especially those describing mathematics and computer software but also chemistry

    oai_token-act-pair · gemini-2.0-flash

    Code and Math

    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
    uities
    -0.46
    '])->
    -0.45
    ->___
    -0.44
    itos
    -0.44
    ->$
    -0.42
     marginTop
    -0.41
     conges
    -0.41
    IRUS
    -0.41
    __["
    -0.40
    γε
    -0.40
    POSITIVE LOGITS
     '\\;'
    0.67
     تضيفلها
    0.63
    RenderAtEndOf
    0.60
    ThemeOverlay
    0.57
    IUrlHelper
    0.55
     Walkover
    0.55
     HasFactory
    0.55
    ariConfig
    0.53
     typelib
    0.53
     quæ
    0.50
    Activations Density 0.646%

    No Known Activations