© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9290
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quality of construction or design, and words with positive connotation

    oai_token-act-pair · gemini-2.0-flash

    words related to quality of craftsmanship or construction

    np_token-act-pair-logits · gpt-4o-mini

    Actions/something being done

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    SourceChecksum
    -0.82
     fufficient
    -0.76
     neceffary
    -0.75
     itſelf
    -0.74
     myſelf
    -0.73
     preſent
    -0.72
     ſeveral
    -0.72
     againſt
    -0.69
     themſelves
    -0.69
     neceſſ
    -0.68
    POSITIVE LOGITS
     designed
    0.67
     played
    0.66
     crafted
    0.62
     drawn
    0.61
     made
    0.61
     edited
    0.57
     constructed
    0.57
     done
    0.57
     maintained
    0.57
     executed
    0.57
    Activations Density 1.356%

    No Known Activations