© 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. 1863
    Prev
    Next
    INDEX
    Explanations

    the phrase "all at"

    oai_token-act-pair · gemini-2.0-flash

    once

    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
     two
    -1.02
    two
    -0.91
    Two
    -0.87
    TWO
    -0.83
     Two
    -0.83
     TWO
    -0.81
     deux
    -0.73
     두
    -0.71
     dois
    -0.68
     Dois
    -0.65
    POSITIVE LOGITS
     once
    0.88
     ONCE
    0.76
     Once
    0.65
    once
    0.64
    Once
    0.60
     sekali
    0.56
     einmal
    0.55
    PMailer
    0.52
    ursal
    0.52
    ONCE
    0.50
    Activations Density 0.890%

    No Known Activations