© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5550
    Prev
    Next
    INDEX
    Explanations

    the first syllable of "Hordeum"

    oai_token-act-pair · gemini-2.0-flash

    words starting with 'Hor'

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

    hor

    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
     متعلقه
    -0.82
     @"/
    -0.75
    AnchorTagHelper
    -0.70
    NameInMap
    -0.67
    matchCondition
    -0.64
     EClass
    -0.62
     تانيه
    -0.58
    BufferException
    -0.56
    الدراسه
    -0.52
     initComponents
    -0.52
    POSITIVE LOGITS
    šnje
    0.49
    ANTAGES
    0.44
    AttributeSet
    0.44
     zucca
    0.44
    SafeArea
    0.43
    цезда
    0.43
    antd
    0.43
     թվական
    0.42
     vė
    0.42
    complexContent
    0.42
    Activations Density 0.395%

    No Known Activations