© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9815
    Prev
    Next
    INDEX
    Explanations

    different forms of the phrase "catch up"

    oai_token-act-pair · gemini-2.0-flash

    catch

    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
     catch
    -3.52
     Catch
    -3.16
     catching
    -3.09
    catch
    -3.08
     caught
    -2.98
     catches
    -2.97
    Catch
    -2.89
     CATCH
    -2.80
    caught
    -2.52
     Caught
    -2.45
    POSITIVE LOGITS
     autorytatywna
    0.60
     שוליים
    0.54
    ThroughAttribute
    0.52
    openhauer
    0.52
    omla
    0.51
    mering
    0.49
    Buildable
    0.48
    NameInMap
    0.47
    inaison
    0.45
    szer
    0.45
    Activations Density 0.906%

    No Known Activations