© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10761
    Prev
    Next
    INDEX
    Explanations

    the word "holding", sometimes alongside articles and common words, and also scores text about districts and buildings

    oai_token-act-pair · gemini-2.0-flash

    holding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     the
    -1.41
     a
    -1.00
    "):
    -0.87
     your
    -0.82
     an
    -0.81
     its
    -0.81
    "])
    -0.80
    ":
    -0.80
    — 
    -0.79
    ."</
    -0.79
    POSITIVE LOGITS
     avoient
    1.02
     ainfi
    0.94
     marseille
    0.90
     parís
    0.90
     feroit
    0.90
     pouvoit
    0.89
     auroit
    0.88
     moschino
    0.88
     laiton
    0.88
     italiane
    0.87
    Activations Density 3.284%

    No Known Activations