© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14115
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation in close proximity to personal pronouns and the word "then"

    oai_token-act-pair · gemini-2.0-flash

    describing things people did

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    &&\
    -0.54
     reinvest
    -0.47
    Was
    -0.47
    :✨
    -0.46
    abandon
    -0.46
    Were
    -0.43
     Were
    -0.43
     conduct
    -0.42
    __*/
    -0.42
    Abandon
    -0.42
    POSITIVE LOGITS
     listened
    0.95
     fished
    0.94
     looked
    0.92
     danced
    0.91
     kept
    0.91
     walked
    0.91
     prayed
    0.91
     searched
    0.91
     waited
    0.90
     acted
    0.90
    Activations Density 3.279%

    No Known Activations