© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6787
    Prev
    Next
    INDEX
    Explanations

    the word "the" in different contexts

    oai_token-act-pair · gemini-2.0-flash

    structural components or settings in a narrative context

    np_token-act-pair-logits · gpt-4o-mini

    the

    np_max-act-logits · gemini-2.0-flash
    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
     للاسماء
    -0.48
    COUVER
    -0.45
     '\\;'
    -0.45
    localScale
    -0.44
    setopt
    -0.43
    Hochspringen
    -0.42
    ($__
    -0.42
     utafitiHapana
    -0.40
    WarningLevel
    -0.40
    cmath
    -0.40
    POSITIVE LOGITS
     heart
    0.66
     background
    0.65
     ejus
    0.63
    TagHelper
    0.63
     lobby
    0.60
    Fiche
    0.60
     middle
    0.59
    écnicas
    0.58
    AttributeSet
    0.57
     center
    0.57
    Activations Density 1.268%

    No Known Activations