© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12538
    Prev
    Next
    INDEX
    Explanations

    words related to imagining things and scenarios

    oai_token-act-pair · gemini-2.0-flash

    hypotheticals/advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    IsContent
    -0.53
    switchTo
    -0.47
    égias
    -0.46
    leyebilirsiniz
    -0.45
    bán
    -0.42
    WebVitals
    -0.41
    ReadInt
    -0.41
     rainbow
    -0.41
    gele
    -0.40
    +#+#
    -0.40
    POSITIVE LOGITS
    RegistryLite
    0.88
    UnknownFieldSet
    0.83
    RegressionTest
    0.75
    complexContent
    0.73
     فريبيس
    0.71
    addCriterion
    0.66
     ?";
    0.66
     للمعارف
    0.66
    AsUp
    0.65
    mpä
    0.65
    Activations Density 1.390%

    No Known Activations