© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14868
    Prev
    Next
    INDEX
    Explanations

    a mixture of words related to specific topics with different origins, possibly for identifying the overall subject using topic modeling or information retrieval techniques.

    oai_token-act-pair · gemini-2.0-flash

    Scientific texts

    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
    han
    -0.61
    exécution
    -0.58
    éclairage
    -0.57
    insegna
    -0.56
    honneur
    -0.56
    Personensuche
    -0.56
     Majefty
    -0.56
    arrivée
    -0.55
     RIPRODUZIONE
    -0.55
    has
    -0.55
    POSITIVE LOGITS
    esist
    0.42
    annotation
    0.42
    ese
    0.41
    ʊ
    0.41
    asin
    0.40
    gebraucht
    0.40
    itons
    0.40
    at
    0.39
    brać
    0.39
    anse
    0.38
    Activations Density 6.342%

    No Known Activations