© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2946
    Prev
    Next
    INDEX
    Explanations

    labels and captions for plots in a scientific paper

    oai_token-act-pair · gemini-2.0-flash

    scientific imaging/analysis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    帖最后由
    -0.72
     MEASURE
    -0.57
    contentLoaded
    -0.51
     SHOWING
    -0.50
    fromnode
    -0.50
     ASSOCIATES
    -0.48
     CHAIRMAN
    -0.47
     diplom
    -0.47
     EXPERIMENTAL
    -0.47
     ejus
    -0.47
    POSITIVE LOGITS
     IndexPath
    0.62
     HST
    0.59
     NTB
    0.56
    исленность
    0.56
     TIR
    0.55
    ípios
    0.54
     SPM
    0.53
    NUMX
    0.53
    مراجع
    0.53
    المراجع
    0.53
    Activations Density 18.329%

    No Known Activations