© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8678
    Prev
    Next
    INDEX
    Explanations

    hyphenated series of capital letters and numbers, especially compiler options

    oai_token-act-pair · gemini-2.0-flash

    hyphen

    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
     kasarigan
    -0.93
    rungsseite
    -0.85
    ThroughAttribute
    -0.78
     onCreateView
    -0.78
    expandindo
    -0.78
     محفوظة
    -0.73
     surla
    -0.71
     GenerationType
    -0.69
    addCriterion
    -0.68
    tagext
    -0.68
    POSITIVE LOGITS
     duy
    0.43
    szön
    0.43
    โน
    0.42
    stüt
    0.42
    di
    0.42
    левой
    0.42
     out
    0.41
    bal
    0.41
    νης
    0.41
    s
    0.40
    Activations Density 1.839%

    No Known Activations