© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4644
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to a minimum quantity

    oai_token-act-pair · gemini-2.0-flash

    minimum or maximum

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     defaultstate
    -0.75
    ThroughAttribute
    -0.69
    WriteBarrier
    -0.69
    abestanden
    -0.68
    AntiForgeryToken
    -0.67
    oredCriteria
    -0.67
    windowFixed
    -0.65
    OGND
    -0.62
     المعيارى
    -0.62
    parsedMessage
    -0.62
    POSITIVE LOGITS
    asticity
    0.49
     charset
    0.48
     />,
    0.47
    ()};
    0.47
    matta
    0.45
    }})
    0.44
    ：“……”
    0.43
    ánchez
    0.43
     length
    0.43
    verbrauch
    0.43
    Activations Density 7.037%

    No Known Activations