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

    the word "towards"

    oai_token-act-pair · gemini-2.0-flash

    towards

    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
     avoient
    -1.38
     étoient
    -1.32
     fermés
    -1.23
     houſe
    -1.21
     normaux
    -1.20
     automatiques
    -1.20
     pauvres
    -1.19
     étoit
    -1.17
     épais
    -1.17
     Theſe
    -1.16
    POSITIVE LOGITS
    ↵↵
    1.03
    ,
    0.82
    .
    0.81
     for
    0.79
     particular
    0.76
    <eos>
    0.76
     a
    0.69
     the
    0.68
     (
    0.68
    -
    0.63
    Activations Density 1.219%

    No Known Activations