© 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. 4448
    Prev
    Next
    INDEX
    Explanations

    words related to included parts and standard settings.

    oai_token-act-pair · gemini-2.0-flash

    code, programming

    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
     default
    -2.03
    default
    -1.79
     Default
    -1.55
     defaults
    -1.54
    Default
    -1.50
    默认
    -1.41
     defaulted
    -1.29
    デフォ
    -1.26
    DEFAULT
    -1.23
     DEFAULT
    -1.23
    POSITIVE LOGITS
    Datuak
    0.77
     ddelweddau
    0.61
     OFDb
    0.54
    RenderAtEndOf
    0.54
    criture
    0.49
     unknownFields
    0.49
    tagHelperRunner
    0.49
     golongan
    0.47
     gerais
    0.46
    invokeLater
    0.46
    Activations Density 0.968%

    No Known Activations