© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6491
    Prev
    Next
    INDEX
    Explanations

    pronouns in close proximity to auxiliary verbs within a sentence

    oai_token-act-pair · gemini-2.0-flash

    News excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     cared
    -1.08
    Loved
    -1.02
     loved
    -0.96
    loved
    -0.94
     looked
    -0.94
     Loved
    -0.93
     LOVED
    -0.88
     Looked
    -0.83
     liked
    -0.83
    looked
    -0.80
    POSITIVE LOGITS
     Got
    0.92
    Got
    0.89
     got
    0.84
    CloseOperation
    0.80
    got
    0.77
     GOT
    0.75
    MemoryWarning
    0.66
    ystema
    0.64
     increased
    0.63
    oa̍t
    0.63
    Activations Density 5.268%

    No Known Activations