© 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. 8056
    Prev
    Next
    INDEX
    Explanations

    strings that look like URLs or accession numbers

    oai_token-act-pair · gemini-2.0-flash

    Source code/technical references

    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
    contentLoaded
    -0.51
    LCA
    -0.50
    TCA
    -0.49
    봐
    -0.47
     LCA
    -0.47
    >());
    -0.46
    BSA
    -0.46
    DPA
    -0.44
    SDA
    -0.44
    mba
    -0.44
    POSITIVE LOGITS
     OMITBAD
    0.68
    tvguidetime
    0.64
    classnames
    0.62
    jsonwebtoken
    0.62
    Chất
    0.59
    يكب
    0.58
    oporosis
    0.58
     referenties
    0.57
    @[+][
    0.56
    izoen
    0.56
    Activations Density 0.962%

    No Known Activations