© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9914
    Prev
    Next
    INDEX
    Explanations

    words related to businesses and their operations, especially in the context of economic viability or maintaining a certain state.

    oai_token-act-pair · gemini-2.0-flash

    ongoing events, maintaining something

    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
     mantenimiento
    -0.58
     stays
    -0.57
    ustain
    -0.57
    tahankan
    -0.57
     trụ
    -0.57
     maintain
    -0.54
     stayed
    -0.54
     mantenerse
    -0.54
    houden
    -0.54
     viewWillAppear
    -0.53
    POSITIVE LOGITS
    OGND
    0.58
    protoc
    0.57
     незавершена
    0.56
    NgModule
    0.53
    出版年
    0.53
    kloped
    0.50
    ActionCreators
    0.49
    nodoc
    0.48
    ToScroll
    0.48
     مشين
    0.48
    Activations Density 2.592%

    No Known Activations