© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1994
    Prev
    Next
    INDEX
    Explanations

    text in languages other than English, especially French and Portuguese, sometimes mixed with English

    oai_token-act-pair · gemini-2.0-flash

    mixed non-English and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     de
    -0.75
     noires
    -0.66
     ouvertes
    -0.60
     voisins
    -0.60
     esprits
    -0.59
    á
    -0.57
     sorella
    -0.57
     couverts
    -0.56
     pauvres
    -0.56
     automatiques
    -0.55
    POSITIVE LOGITS
     مواليد
    0.60
     snippetHide
    0.58
     EconPapers
    0.56
     ModelExpression
    0.55
     BoxFit
    0.54
    Бахар
    0.54
    RTEX
    0.54
     ExecuteAsync
    0.52
    jména
    0.52
    matchCondition
    0.51
    Activations Density 1.698%

    No Known Activations