© 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. 653
    Prev
    Next
    INDEX
    Explanations

    dates and titles related to authority figures

    oai_token-act-pair · gemini-2.0-flash

    days or months

    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
     itſelf
    -0.94
     myſelf
    -0.78
     crdi
    -0.77
     holotype
    -0.75
     BoxFit
    -0.74
     moschino
    -0.69
     purpoſe
    -0.69
     poffible
    -0.68
     Efq
    -0.68
     photolibrary
    -0.67
    POSITIVE LOGITS
     समीक्षाओं
    0.46
    دانشنامهٔ
    0.41
    simi
    0.41
     sopr
    0.41
     having
    0.41
    contentLoaded
    0.40
    Revenir
    0.38
    허
    0.37
     tener
    0.37
     while
    0.37
    Activations Density 5.298%

    No Known Activations