© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3325
    Prev
    Next
    INDEX
    Explanations

    HTML language tags and also URLs containing "translate.google.com"

    oai_token-act-pair · gemini-2.0-flash

    language attributes in HTML

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

    code and language tags

    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
    tonode
    -0.57
    Verwendung
    -0.55
     enfans
    -0.54
    Amérique
    -0.52
    исленность
    -0.51
    ftest
    -0.51
    mergeFrom
    -0.50
    #+#
    -0.50
    cjon
    -0.48
     beginnetje
    -0.48
    POSITIVE LOGITS
     lenker
    0.53
    vi
    0.52
     مشين
    0.50
     Jair
    0.48
    CardContent
    0.47
     katal
    0.47
     cucchiai
    0.46
    jat
    0.46
    pe
    0.46
    instancetype
    0.45
    Activations Density 0.730%

    No Known Activations