© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15712
    Prev
    Next
    INDEX
    Explanations

    a seemingly random assortment of alphanumeric character combinations

    oai_token-act-pair · gemini-2.0-flash

    code, URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    gk
    -0.84
    sdf
    -0.79
    tst
    -0.75
    vj
    -0.73
    rj
    -0.73
    mbs
    -0.68
     Г
    -0.66
    sld
    -0.65
    CLS
    -0.65
    isr
    -0.65
    POSITIVE LOGITS
    Autoritní
    1.19
     propOrder
    1.18
    ftagPool
    1.15
    MigrationBuilder
    1.13
    oa̍t
    1.12
     Roskov
    1.05
    ьаж
    1.02
    GEBURTSDATUM
    0.99
    webElementXpaths
    0.98
    httphttps
    0.98
    Activations Density 4.557%

    No Known Activations