© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 12559
    Prev
    Next
    INDEX
    Explanations

    the word-pairs "with the", "on the", "of the", "in the" or other prepositions followed by "the"

    oai_token-act-pair · gemini-2.0-flash

    say "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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     ویکی‌پدیای
    -0.58
    Abitanti
    -0.57
    rolid
    -0.55
    mstyle
    -0.54
    CppMethod
    -0.53
    ukone
    -0.53
     "..\..\..\
    -0.52
    
    -0.52
    Pyx
    -0.52
     davon
    -0.52
    POSITIVE LOGITS
     the
    1.37
    The
    1.10
     The
    1.02
     tbe
    0.70
     THE
    0.68
    the
    0.65
    sthe
    0.65
    enthe
    0.64
    esthe
    0.62
    ethe
    0.62
    Activations Density 2.585%

    No Known Activations