© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8647
    Prev
    Next
    INDEX
    Explanations

    instances of the letters "A", "L", "CA", or "FF" and also the prefix "UNA"

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     "..\..\..\
    -0.73
    parsedMessage
    -0.65
     "..\..\
    -0.65
     Chrift
    -0.62
     Chriſt
    -0.59
    piram
    -0.59
     Dostupné
    -0.59
    graphed
    -0.58
    OrNil
    -0.58
    localctx
    -0.57
    POSITIVE LOGITS
    setVerticalGroup
    0.47
    DrawerLayout
    0.45
    ظهار
    0.45
    ूट
    0.43
     la
    0.43
     nim
    0.42
    AxisAlignment
    0.41
    JoinColumn
    0.41
    findpost
    0.40
     propOrder
    0.40
    Activations Density 0.802%

    No Known Activations