© 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. 14365
    Prev
    Next
    INDEX
    Explanations

    horizontal lines in a document

    oai_token-act-pair · gemini-2.0-flash

    Hyphens

    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
    InjectAttribute
    -0.94
    PerformLayout
    -0.92
    AndEndTag
    -0.91
    WebVitals
    -0.85
    ftagPool
    -0.84
    RepeatedField
    -0.78
     kasarigan
    -0.77
    GEBURTSDATUM
    -0.75
    ########.
    -0.75
    RegressionTest
    -0.74
    POSITIVE LOGITS
     biểu
    0.46
    othesis
    0.42
    Curs
    0.41
     testSet
    0.40
    endfor
    0.39
    ERM
    0.39
    targ
    0.38
    rawDesc
    0.38
    tempts
    0.38
    jiri
    0.38
    Activations Density 0.001%

    No Known Activations