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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5356
    Prev
    Next
    INDEX
    Explanations

    the word "in" followed by something

    oai_token-act-pair · gemini-2.0-flash

    symbols and special characters

    np_token-act-pair-logits · gpt-4o-mini

    in vitro, in vivo

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    <em>
    -1.73
    <i>
    -1.67
    /*
    -0.92
     /*
    -0.80
    《
    -0.78
     _
    -0.68
    textit
    -0.61
    /*
    -0.60
     《
    -0.60
     『
    -0.58
    POSITIVE LOGITS
    kháu
    0.69
    ]\\
    0.69
    Personensuche
    0.68
     InputDecoration
    0.65
     BoxFit
    0.64
     المعيارى
    0.60
    SharedCtor
    0.60
     الاطلاع
    0.60
    setVerticalGroup
    0.59
    :✨
    0.59
    Activations Density 2.244%

    No Known Activations