© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2912
    Prev
    Next
    INDEX
    Explanations

    mentions of 'short amount of time' or similar phrases.

    oai_token-act-pair · gemini-2.0-flash

    short

    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
    Negative Logits
     paille
    -0.52
     habet
    -0.52
    phrine
    -0.51
     transfieras
    -0.49
     pleaſure
    -0.48
     femininas
    -0.48
     purpoſe
    -0.47
    aarrggbb
    -0.47
     quæ
    -0.46
     prestation
    -0.45
    POSITIVE LOGITS
     short
    3.56
    short
    3.03
     Short
    2.98
    Short
    2.94
     SHORT
    2.81
    SHORT
    2.55
    短
    2.23
     shortest
    2.09
     shor
    2.09
     shorter
    2.09
    Activations Density 1.576%

    No Known Activations