© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13517
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to ownership, direction, or management of people or entities

    oai_token-act-pair · gemini-2.0-flash

    management

    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
     ModelExpression
    -0.68
    awtextra
    -0.59
     continúas
    -0.45
     ujednoznacz
    -0.45
    PageContext
    -0.43
    hyrchwyd
    -0.43
    opardy
    -0.42
    AsUp
    -0.42
    reiter
    -0.42
    ELEMENTS
    -0.42
    POSITIVE LOGITS
     purpoſe
    0.66
     poffe
    0.66
    DOCTYPE
    0.65
     poffible
    0.61
     Majefty
    0.60
     Conſ
    0.60
     faſt
    0.59
     Eſ
    0.59
    ſelf
    0.59
     peindre
    0.59
    Activations Density 1.015%

    No Known Activations