© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4240
    Prev
    Next
    INDEX
    Explanations

    the word "the" when preceded by certain prepositions or conjunctions

    oai_token-act-pair · gemini-2.0-flash

    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_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     perna
    -0.50
    NOPQRST
    -0.48
     pubblic
    -0.42
    Fully
    -0.40
     dipende
    -0.39
     the
    -0.39
     Fully
    -0.38
    generics
    -0.38
     perfettamente
    -0.38
     cubre
    -0.38
    POSITIVE LOGITS
    NameInMap
    0.85
    invokeLater
    0.76
    OrNil
    0.74
     дописавши
    0.73
    Lähteet
    0.73
     fact
    0.70
    SourceChecksum
    0.67
    uxxxx
    0.65
     ModelExpression
    0.64
     need
    0.63
    Activations Density 3.018%

    No Known Activations