© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3374
    Prev
    Next
    INDEX
    Explanations

    dates, times, activities and locations

    oai_token-act-pair · gemini-2.0-flash

    Events and schedules

    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
    tvguidetime
    -1.02
    endphp
    -0.97
    +:+
    -0.97
    webElementGuid
    -0.96
    WriteTagHelper
    -0.96
     Roskov
    -0.96
     InputDecoration
    -0.87
     iprot
    -0.86
     CreateTagHelper
    -0.84
    fromnode
    -0.82
    POSITIVE LOGITS
     on
    0.50
     through
    0.49
     at
    0.46
    ದು
    0.45
     {
    0.43
    ures
    0.42
    isi
    0.42
    ud
    0.40
    indo
    0.40
     Gray
    0.40
    Activations Density 2.616%

    No Known Activations