© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11377
    Prev
    Next
    INDEX
    Explanations

    French language constructs using "ai", "eu", "est", or "as."

    oai_token-act-pair · gemini-2.0-flash

    ai

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     &___
    -0.73
    팎
    -0.71
    iNdEx
    -0.70
    sträger
    -0.66
    SpringRunner
    -0.65
    protector
    -0.65
    Còn
    -0.64
    rahman
    -0.63
     合集
    -0.62
    parsedMessage
    -0.60
    POSITIVE LOGITS
     been
    0.98
    been
    0.92
     have
    0.82
     has
    0.81
    have
    0.79
    ve
    0.74
    Been
    0.72
     had
    0.68
    <bos>
    0.67
     hebben
    0.66
    Activations Density 0.919%

    No Known Activations