© 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. 4929
    Prev
    Next
    INDEX
    Explanations

    strings ending in 'ing' with possible preceding characters

    oai_token-act-pair · gemini-2.0-flash

    words ending in 'ing'

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

    sing

    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
     bandes
    -0.42
     Lawson
    -0.41
     bande
    -0.41
     spä
    -0.40
    uni
    -0.39
    GeneratedValue
    -0.39
    нали
    -0.38
     bis
    -0.37
    apimachinery
    -0.37
     opri
    -0.35
    POSITIVE LOGITS
    led
    0.98
    Personensuche
    0.85
    RegressionTest
    0.83
    lero
    0.82
    leness
    0.82
    lename
    0.81
    twimg
    0.81
    lest
    0.81
    les
    0.78
    lec
    0.78
    Activations Density 1.385%

    No Known Activations