© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12882
    Prev
    Next
    INDEX
    Explanations

    code notations, which include array indexing, mathematical symbols and other programming language elements

    oai_token-act-pair · gemini-2.0-flash

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Personendaten
    -0.84
    NameInMap
    -0.71
    adaptiveStyles
    -0.59
    yntaxException
    -0.58
    MockBean
    -0.56
    RenderAtEndOf
    -0.56
    Personensuche
    -0.55
     Drapeau
    -0.55
    verwijspagina
    -0.55
    AsUp
    -0.55
    POSITIVE LOGITS
     שוליים
    0.53
     hiér
    0.48
     specchio
    0.47
     dương
    0.47
    unité
    0.46
     drit
    0.46
     sammen
    0.45
     houſe
    0.43
     magique
    0.43
    vila
    0.43
    Activations Density 0.601%

    No Known Activations