© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14354
    Prev
    Next
    INDEX
    Explanations

    code that has the number 1 followed by other code characters or numbers

    oai_token-act-pair · gemini-2.0-flash

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Glej
    -0.51
    babu
    -0.50
    fer
    -0.47
     rather
    -0.47
    ysk
    -0.46
     Italiana
    -0.46
    bey
    -0.45
     ốc
    -0.45
    жений
    -0.45
    ey
    -0.44
    POSITIVE LOGITS
    SequentialGroup
    0.79
    ^(@)
    0.74
     contextLoads
    0.71
    ombic
    0.68
    WriteTagHelper
    0.63
    ]='\
    0.63
     Waray
    0.62
     HttpNotFound
    0.62
    ]";
    0.61
    IntoConstraints
    0.60
    Activations Density 2.002%

    No Known Activations