© 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. 14668
    Prev
    Next
    INDEX
    Explanations

    the word "over" and certain prepositions.

    oai_token-act-pair · gemini-2.0-flash

    the word "over"

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

    over/under

    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
    spreis
    -0.64
    ----</
    -0.63
    fillType
    -0.59
    GRAFÍA
    -0.59
     becauſe
    -0.58
    hdessä
    -0.58
    **
    -0.57
     avoient
    -0.56
    tranno
    -0.56
     SUITE
    -0.54
    POSITIVE LOGITS
    line
    0.46
     насељу
    0.45
     Line
    0.45
    WithMany
    0.45
    pushFollow
    0.45
     चीज़ों
    0.44
     ModelExpression
    0.44
    sy
    0.44
    Line
    0.43
    ys
    0.42
    Activations Density 1.076%

    No Known Activations