© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6448
    Prev
    Next
    INDEX
    Explanations

    bracketed citations

    oai_token-act-pair · gemini-2.0-flash

    research paper citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    si
    -0.52
    se
    -0.51
    ap
    -0.48
    cha
    -0.47
    la
    -0.47
    par
    -0.46
    ca
    -0.46
    ba
    -0.46
    li
    -0.46
    ch
    -0.45
    POSITIVE LOGITS
    rungsseite
    0.65
     resourceCulture
    0.62
     betweenstory
    0.59
    Personensuche
    0.58
     estekak
    0.57
     الحره
    0.57
    دانشنامهٔ
    0.57
     disambiguazione
    0.56
    MigrationBuilder
    0.56
    GEBURTSDATUM
    0.56
    Activations Density 10.037%

    No Known Activations