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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 311
    Prev
    Next
    INDEX
    Explanations

    parts of an XML file, particularly related to questions and answers ("reponse", "question", "categorie", "mauvaiseReponse", "bonneReponse").

    oai_token-act-pair · gemini-2.0-flash

    Possibly code/data

    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
    ArrowToggle
    -0.69
    CloseOperation
    -0.54
    SpringBootTest
    -0.49
    ]();
    -0.49
    ")));
    -0.47
     Walkover
    -0.47
    ++){
    -0.47
    AnchorStyles
    -0.45
    AndEndTag
    -0.45
    WithFormat
    -0.44
    POSITIVE LOGITS
     CURLOPT
    0.56
    Coordonnées
    0.56
     idéia
    0.55
     Voulez
    0.55
    Musée
    0.54
    Elles
    0.53
    Œuvres
    0.52
    livre
    0.51
     Coeur
    0.50
    Détails
    0.50
    Activations Density 36.352%

    No Known Activations