© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13313
    Prev
    Next
    INDEX
    Explanations

    uses of "of" and "part" with an activation boost with the words "term", "wake", "end","due", and " border"

    oai_token-act-pair · gemini-2.0-flash

    formal writing

    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
     XNUMX
    -0.63
     ofthe
    -0.59
    <bos>
    -0.58
     pleaſure
    -0.51
     noDo
    -0.50
    TagMode
    -0.47
    they
    -0.46
     Poincar
    -0.45
    IsContent
    -0.44
     Shakspeare
    -0.44
    POSITIVE LOGITS
    oule
    0.77
     Pollack
    0.72
    tritt
    0.71
    inova
    0.71
    celli
    0.70
    ianum
    0.70
     tubos
    0.69
    ÍT
    0.69
    IMAN
    0.68
    hena
    0.67
    Activations Density 2.934%

    No Known Activations