© 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. 2518
    Prev
    Next
    INDEX
    Explanations

    the words 'the', 'in', and other common short words

    oai_token-act-pair · gemini-2.0-flash

    locations or elements in a setting

    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
    OrBuilder
    -0.54
     dignité
    -0.50
     createState
    -0.48
     trouvera
    -0.47
    uxxxx
    -0.45
    addCriterion
    -0.44
     chegada
    -0.43
     défaite
    -0.42
    GNA
    -0.42
     leçon
    -0.42
    POSITIVE LOGITS
    ValueStyle
    0.75
     passage
    0.70
     sewers
    0.69
     courtyard
    0.66
     lake
    0.66
     stairs
    0.66
     cave
    0.65
     waterfall
    0.65
     cliffs
    0.65
     mountains
    0.63
    Activations Density 1.649%

    No Known Activations