© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6161
    Prev
    Next
    INDEX
    Explanations

    the word "embrace", sometimes near "perfect" or "inter" prefixes, and sometimes near the word "came" or mentions of parents

    oai_token-act-pair · gemini-2.0-flash

    embrace

    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
     
    -1.00
     and
    -0.91
     of
    -0.86
     in
    -0.84
     (
    -0.79
     as
    -0.78
     he
    -0.78
     S
    -0.76
     The
    -0.76
     E
    -0.75
    POSITIVE LOGITS
     auffi
    1.66
     Monfieur
    1.66
     auroit
    1.58
     étoit
    1.55
     feroit
    1.54
     ainfi
    1.52
     ſever
    1.48
     avoient
    1.46
     pouvoit
    1.43
     étoient
    1.41
    Activations Density 2.350%

    No Known Activations