© 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. 16146
    Prev
    Next
    INDEX
    Explanations

    references to sewing, designing, crafting, and cooking and other creative hobbies.

    oai_token-act-pair · gemini-2.0-flash

    hobbies and activities

    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
     näky
    -0.49
     estekak
    -0.48
     AssemblyCulture
    -0.46
     démocr
    -0.41
     autorités
    -0.39
     détru
    -0.38
     estándares
    -0.38
     spä
    -0.37
     pouvoirs
    -0.37
     frek
    -0.37
    POSITIVE LOGITS
     actionMode
    0.78
    StoryboardSegue
    0.76
     this
    0.76
     the
    0.75
     their
    0.75
    __(/*!
    0.71
     those
    0.70
     it
    0.70
    TagHelper
    0.69
    XtraEditors
    0.69
    Activations Density 11.573%

    No Known Activations