© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6932
    Prev
    Next
    INDEX
    Explanations

    text related to groups of people and places as well as words that sound like rights.

    oai_token-act-pair · gemini-2.0-flash

    quality, standards

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Visit
    -0.67
     Deceased
    -0.65
     Return
    -0.62
     Encounter
    -0.58
    Return
    -0.57
     Residence
    -0.57
    InstanceState
    -0.56
     Out
    -0.54
    EOUT
    -0.54
    Rhestr
    -0.54
    POSITIVE LOGITS
     Quality
    0.78
     Superior
    0.77
     Standards
    0.74
    Quality
    0.72
    Superior
    0.71
     Capability
    0.69
     Worth
    0.66
     Simplicity
    0.66
    DockStyle
    0.66
    Standards
    0.65
    Activations Density 10.881%

    No Known Activations