© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16148
    Prev
    Next
    INDEX
    Explanations

    words that begin with "reg", especially when followed by a vowel, and also some words related to winter or holidays

    oai_token-act-pair · gemini-2.0-flash

    say "reg" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Билгалдахарш
    -0.61
     initComponents
    -0.60
     gynnwys
    -0.54
     كومونز
    -0.52
     ContentValues
    -0.47
    Jeografia
    -0.44
    ecore
    -0.44
     RSSSF
    -0.43
    bedaan
    -0.43
     Obrigado
    -0.43
    POSITIVE LOGITS
    lair
    0.62
    TagHelper
    0.61
    tabular
    0.60
    nitive
    0.59
    rillo
    0.57
    rowth
    0.57
    rini
    0.54
    rui
    0.54
    lue
    0.54
    rande
    0.53
    Activations Density 7.666%

    No Known Activations