© 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. 5482
    Prev
    Next
    INDEX
    Explanations

    floating point numbers starting with "0.2", "0.5", or "0.7", and also finds the micro symbol for micrograms

    oai_token-act-pair · gemini-2.0-flash

    numeric values and programming related terms

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

    5

    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
     Infórmanos
    -0.47
    Occurred
    -0.47
    MethodManager
    -0.46
     ModelExpression
    -0.44
    ințe
    -0.44
     Wyn
    -0.44
    PhysRevD
    -0.43
     Eight
    -0.42
    ients
    -0.42
    سطس
    -0.40
    POSITIVE LOGITS
    5
    0.96
     pě
    0.68
    __':
    0.65
    ５
    0.64
    mainloop
    0.63
    Зноскі
    0.61
     AspNetCore
    0.61
    𝟱
    0.59
    NegativeButton
    0.57
    portál
    0.57
    Activations Density 2.123%

    No Known Activations