© 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. 9532
    Prev
    Next
    INDEX
    Explanations

    snippets of conversational style language and numbered lists or grants.

    oai_token-act-pair · gemini-2.0-flash

    research funding

    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
    geordnete
    -0.57
    yarnpkg
    -0.52
     CreateTagHelper
    -0.52
     للاسماء
    -0.52
     يتيمه
    -0.51
    HostException
    -0.49
    גרפיה
    -0.48
    SUNG
    -0.48
    cvtColor
    -0.48
     AssemblyTitle
    -0.47
    POSITIVE LOGITS
     Biro
    0.48
    itní
    0.47
     lenker
    0.47
    OGND
    0.47
    :✨
    0.47
    reggio
    0.44
    ("#{
    0.44
    ποίη
    0.44
     Joaquim
    0.44
     formData
    0.43
    Activations Density 0.537%

    No Known Activations