© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1981
    Prev
    Next
    INDEX
    Explanations

    phrases related to helping, rescue, and saving.

    oai_token-act-pair · gemini-2.0-flash

    Pulled

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Wikimedijinoj
    -0.87
     ModelExpression
    -0.86
    DeleteBehavior
    -0.86
    queryInterface
    -0.84
    Gön
    -0.84
    mybatisplus
    -0.82
     AssemblyCulture
    -0.78
     Référence
    -0.78
     quæ
    -0.78
     esternos
    -0.77
    POSITIVE LOGITS
     over
    0.47
     process
    0.45
     C
    0.42
     по
    0.42
    orge
    0.41
     on
    0.40
    ed
    0.39
    ानी
    0.38
     even
    0.38
     po
    0.38
    Activations Density 0.635%

    No Known Activations