© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6935
    Prev
    Next
    INDEX
    Explanations

    mentions of time

    oai_token-act-pair · gemini-2.0-flash

    numerical values or representations

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

    numbers

    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
     ModelExpression
    -0.82
    存于互联网档案馆
    -0.81
     الحره
    -0.81
     المعيارى
    -0.81
     ujednoznacz
    -0.80
     '\\;'
    -0.78
     صوتيه
    -0.78
    Décès
    -0.78
     متعلقه
    -0.78
     חיצוניים
    -0.76
    POSITIVE LOGITS
     
    1.34
    7
    0.65
    8
    0.64
    9
    0.62
    6
    0.52
     nueve
    0.50
    ９
    0.49
     ۷
    0.47
    ８
    0.47
    ７
    0.47
    Activations Density 1.495%

    No Known Activations