© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8189
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussing something with people, or a description is being provided.

    oai_token-act-pair · gemini-2.0-flash

    filler words in writing

    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
     виправивши
    -1.22
     betweenstory
    -1.16
    SequentialGroup
    -1.10
    ImageContext
    -1.09
     CreateTagHelper
    -1.09
    bootstrapcdn
    -1.02
     Theſe
    -1.02
     myſelf
    -1.00
    parsedMessage
    -1.00
    ⓧ
    -1.00
    POSITIVE LOGITS
     pro
    0.51
    </i>
    0.47
     app
    0.46
     Pro
    0.45
    …
    0.45
    <eos>
    0.43
     ob
    0.43
    御
    0.43
     ge
    0.43
     ag
    0.43
    Activations Density 2.746%

    No Known Activations