© 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. 14105
    Prev
    Next
    INDEX
    Explanations

    words related to law, medicine, research and reporting

    oai_token-act-pair · gemini-2.0-flash

    Shard

    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
    تقاوى
    -0.82
     nahilalakip
    -0.73
     linkovi
    -0.60
    IVEREF
    -0.59
    rahat
    -0.57
    verwijspagina
    -0.56
    ViewFeatures
    -0.55
    Morfologia
    -0.54
    erunner
    -0.53
    ########.
    -0.52
    POSITIVE LOGITS
    ⓧ
    0.76
    ignac
    0.52
    clerview
    0.52
    InjectMocks
    0.51
     اختیار
    0.50
    TabbedPane
    0.49
     esterni
    0.48
    inosau
    0.47
    phanie
    0.47
    burnt
    0.47
    Activations Density 1.751%

    No Known Activations