© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 58
    Prev
    Next
    INDEX
    Explanations

    future tense verbs and nouns or phrases which often modify them

    oai_token-act-pair · gemini-2.0-flash

    offering something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     taken
    -1.09
     Taken
    -0.95
     TAKEN
    -0.93
     ExecuteAsync
    -0.87
    taken
    -0.84
    Taken
    -0.83
    таратура
    -0.81
    \{\\
    -0.75
     ujednoznacz
    -0.75
    shot
    -0.73
    POSITIVE LOGITS
     provided
    0.77
    provided
    0.72
     Provided
    0.70
    Provided
    0.61
     supplied
    0.59
     developed
    0.58
     PROVIDED
    0.57
    cshtml
    0.56
     tartalomajánló
    0.51
    developed
    0.49
    Activations Density 7.827%

    No Known Activations