© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4548
    Prev
    Next
    INDEX
    Explanations

    the word "the"

    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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    IntoConstraints
    -0.75
     tartalomajánló
    -0.60
    Климат
    -0.59
    SourceChecksum
    -0.57
    ContentAsync
    -0.57
    Koordinaten
    -0.56
     âgées
    -0.53
    ConstraintMaker
    -0.50
    RectangleBorder
    -0.50
     gql
    -0.50
    POSITIVE LOGITS
     autorytatywna
    0.69
    elsif
    0.59
    ]")]
    0.59
    araoh
    0.54
    悴
    0.53
     double
    0.52
    Биография
    0.52
    BIOGRAPHY
    0.51
    calaureate
    0.51
    roupe
    0.51
    Activations Density 0.977%

    No Known Activations