© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10834
    Prev
    Next
    INDEX
    Explanations

    JSON format data and the keys often found in them like id, names, role.

    oai_token-act-pair · gemini-2.0-flash

    id

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    MigrationBuilder
    -1.30
    GEBURTSDATUM
    -1.29
     pinulongan
    -1.27
    دانشنامهٔ
    -1.23
    ContentAsync
    -1.23
     дописавши
    -1.16
    ंदीखरीदारी
    -1.14
     initComponents
    -1.13
    tagHelperRunner
    -1.12
    webElementXpaths
    -1.11
    POSITIVE LOGITS
    (
    0.56
    <eos>
    0.55
    b
    0.49
    int
    0.46
    le
    0.45
    +
    0.44
    rs
    0.44
    m
    0.43
    om
    0.43
      
    0.42
    Activations Density 11.237%

    No Known Activations