© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11435
    Prev
    Next
    INDEX
    Explanations

    elements and syntax from programming languages, such as variable assignments, operators, and function definitions

    oai_token-act-pair · gemini-2.0-flash

    words with unusual or archaic spelling

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

    assignment/comparison operators

    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
     di
    -1.09
     v
    -1.07
     V
    -1.05
     T
    -1.05
     M
    -1.04
     I
    -1.03
     K
    -1.03
     
    -1.02
     de
    -1.02
     B
    -1.01
    POSITIVE LOGITS
     itſelf
    2.05
     myſelf
    1.81
     Reſ
    1.77
     greateſt
    1.76
     pleaſure
    1.73
     raiſ
    1.72
     Monfieur
    1.71
     ſche
    1.69
     houſe
    1.66
     uſed
    1.66
    Activations Density 4.769%

    No Known Activations