© 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. 10546
    Prev
    Next
    INDEX
    Explanations

    text at the end of a sentence or paragraph that includes a time period or location

    oai_token-act-pair · gemini-2.0-flash

    say "of"

    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
     Wikimedijinoj
    -0.66
    aarrggbb
    -0.66
    ftagPool
    -0.65
    muñ
    -0.58
    thâu
    -0.56
    CPtr
    -0.56
    mentaux
    -0.55
     tjän
    -0.54
    AndEndTag
    -0.54
     wikipagina
    -0.52
    POSITIVE LOGITS
     of
    0.68
     lines
    0.52
    Lähteet
    0.52
     line
    0.50
     breaks
    0.44
    ereço
    0.43
    Réponse
    0.42
     Bell
    0.41
    hamcrest
    0.41
     Keyes
    0.40
    Activations Density 13.921%

    No Known Activations