© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1164
    Prev
    Next
    INDEX
    Explanations

    the word "once" or "fois" followed by common words

    oai_token-act-pair · gemini-2.0-flash

    French and "once"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     EconPapers
    -0.61
    <bos>
    -0.56
     chère
    -0.54
    indest
    -0.53
     ainfi
    -0.52
    GenerationType
    -0.50
     favorita
    -0.50
     împre
    -0.49
     aéri
    -0.49
     الحره
    -0.49
    POSITIVE LOGITS
     chi̍t
    0.75
    esez
    0.71
    undai
    0.66
    المكان
    0.61
    ClientSize
    0.61
    ñal
    0.60
    ResumeLayout
    0.57
    afficheront
    0.57
    Obrázky
    0.56
     CascadeType
    0.56
    Activations Density 2.694%

    No Known Activations