© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3937
    Prev
    Next
    INDEX
    Explanations

    titles and names of people associated with collections of short fiction, especially in the science fiction genre.

    oai_token-act-pair · gemini-2.0-flash

    short stories

    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
     StatelessWidget
    -0.96
     authors
    -0.88
    Authors
    -0.87
     Authors
    -0.86
     esternos
    -0.83
     StatefulWidget
    -0.80
    ollectionView
    -0.79
    AutoField
    -0.77
     author
    -0.75
     writers
    -0.75
    POSITIVE LOGITS
     stand
    0.55
    stand
    0.48
     short
    0.47
     non
    0.46
    ალ
    0.45
    tiana
    0.45
    fuse
    0.44
    HomeAsUpEnabled
    0.44
     std
    0.43
    abay
    0.43
    Activations Density 0.824%

    No Known Activations