© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14559
    Prev
    Next
    INDEX
    Explanations

    transition words and discourse markers

    oai_token-act-pair · gemini-2.0-flash

    Transitions and alternative viewpoints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    subsubsection
    -0.61
     also
    -0.57
    abestanden
    -0.57
     ویکی‌پدیای
    -0.53
    횟
    -0.50
    Con
    -0.50
    ↵
    -0.49
    Marne
    -0.48
    j
    -0.48
     snippetHide
    -0.48
    POSITIVE LOGITS
     Efq
    0.66
    ValueStyle
    0.63
     كومونز
    0.62
     HasFactory
    0.62
    ^(@)
    0.60
    ыгана
    0.59
     CreateTagHelper
    0.58
     StatelessWidget
    0.57
     gawas
    0.57
    enderror
    0.56
    Activations Density 0.309%

    No Known Activations