© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6035
    Prev
    Next
    INDEX
    Explanations

    the word "depending"

    oai_token-act-pair · gemini-2.0-flash

    depending

    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
    )");
    -1.59
     Theſe
    -1.52
    "]);
    -1.52
    ſelf
    -1.51
     itſelf
    -1.50
    ."));
    -1.48
     myſelf
    -1.46
     Monfieur
    -1.45
     Efq
    -1.44
    )";
    -1.44
    POSITIVE LOGITS
    2
    1.04
    0
    1.02
    1
    0.99
    4
    0.93
    ,
    0.93
    3
    0.92
     (
    0.91
     
    0.90
    -
    0.87
    6
    0.87
    Activations Density 2.022%

    No Known Activations