© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10069
    Prev
    Next
    INDEX
    Explanations

    text relating to performing tests or analysis, especially when time, resources or effort are being used

    oai_token-act-pair · gemini-2.0-flash

    Time-consuming and expensive

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Shahid
    -0.53
    chea
    -0.53
    ()',
    -0.52
    IMA
    -0.51
     neutrals
    -0.50
    </thead>
    -0.50
    asso
    -0.49
     tob
    -0.49
     "'");
    -0.49
    fore
    -0.49
    POSITIVE LOGITS
     CreateTagHelper
    0.66
    脚注の使い方
    0.52
    الحياه
    0.52
    ButterKnife
    0.49
    AddTagHelper
    0.48
     gynnwys
    0.47
     overhead
    0.47
    ::__
    0.46
    imageio
    0.45
    parseFrom
    0.45
    Activations Density 4.033%

    No Known Activations