© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10531
    Prev
    Next
    INDEX
    Explanations

    the word "over" and words that relate to writing

    oai_token-act-pair · gemini-2.0-flash

    Over

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Gemeinden
    -0.62
     puntata
    -0.48
    yakarta
    -0.48
    fowl
    -0.45
     vendo
    -0.44
    borderTop
    -0.43
    באנגלית
    -0.43
    jbl
    -0.42
    noaa
    -0.41
    sind
    -0.41
    POSITIVE LOGITS
    ings
    1.60
    INGS
    1.27
    ize
    0.86
     protoimpl
    0.82
    WithIOException
    0.79
    izing
    0.77
    __*/
    0.76
     AssemblyCulture
    0.75
    ingly
    0.73
    istically
    0.73
    Activations Density 2.643%

    No Known Activations