© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13175
    Prev
    Next
    INDEX
    Explanations

    the word "shot," sometimes paired with related words like "single," or words indicating individual things, like "each" or "person"

    oai_token-act-pair · gemini-2.0-flash

    single-shot

    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
     enfans
    -0.83
     Grecs
    -0.81
     hâte
    -0.79
    seamnă
    -0.78
     démocr
    -0.77
     chrétiens
    -0.76
     feroit
    -0.76
    bibfield
    -0.75
     financière
    -0.73
     chré
    -0.73
    POSITIVE LOGITS
    ↵↵
    0.56
    underbrace
    0.54
    basicConfig
    0.52
    <bos>
    0.51
    TRIBUN
    0.51
    hdashline
    0.49
    差
    0.48
    悠
    0.48
    osoever
    0.48
    dafx
    0.48
    Activations Density 1.507%

    No Known Activations