© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7737
    Prev
    Next
    INDEX
    Explanations

    the word "mark" or "marks", often used in the context of time or other reference point.

    oai_token-act-pair · gemini-2.0-flash

    mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     mark
    -3.11
     marks
    -2.72
    mark
    -2.70
     MARK
    -2.61
     Mark
    -2.58
    Mark
    -2.56
    marks
    -2.48
    MARK
    -2.42
     marked
    -2.36
     Marks
    -2.33
    POSITIVE LOGITS
    ########.
    0.52
    MeasureSpec
    0.49
    SEQUENCE
    0.47
    PRWEB
    0.46
    engertian
    0.46
    antMatchers
    0.46
    ubernur
    0.42
    mäß
    0.42
    ederal
    0.41
    bolo
    0.40
    Activations Density 0.281%

    No Known Activations