© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9776
    Prev
    Next
    INDEX
    Explanations

    words in languages other than English

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Efq
    -0.67
    )";
    -0.65
    ̍t
    -0.65
    )"),
    -0.64
    AndEndTag
    -0.64
    verwijspagina
    -0.63
    EndProject
    -0.63
     Italijani
    -0.63
    AddTagHelper
    -0.61
    "]}
    -0.61
    POSITIVE LOGITS
    yfik
    0.34
     absolutely
    0.33
    ym
    0.33
     حس
    0.33
    rare
    0.32
    segna
    0.31
    ej
    0.31
    lenen
    0.31
     ambas
    0.31
    is
    0.31
    Activations Density 0.204%

    No Known Activations