© 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. 4824
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to electrical engineering and signal processing, particularly interference, current, and signal strength

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "problem"

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

    Problems

    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
     betweenstory
    -0.71
     ModelExpression
    -0.59
    IInterface
    -0.56
     esq
    -0.52
    smithy
    -0.52
    PhysRev
    -0.50
    łec
    -0.49
     linkovi
    -0.49
     sml
    -0.48
     makeStyles
    -0.47
    POSITIVE LOGITS
     problem
    0.80
     problems
    0.76
    problems
    0.69
    problem
    0.69
     Problem
    0.69
    问题
    0.67
     probleem
    0.66
     Problems
    0.65
    PROBLEM
    0.65
     problema
    0.65
    Activations Density 8.204%

    No Known Activations