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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5688
    Prev
    Next
    INDEX
    Explanations

    words related to doors or the interior of buildings

    oai_token-act-pair · gemini-2.0-flash

    uncommon or non-English words

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     thread
    -0.85
     Thread
    -0.76
     threads
    -0.75
    Thread
    -0.75
    thread
    -0.74
    threads
    -0.59
     THREAD
    -0.56
     Threads
    -0.54
    线程
    -0.54
    THREAD
    -0.52
    POSITIVE LOGITS
    uxxxx
    0.76
    المناصب
    0.71
    enterOuterAlt
    0.69
     stiefel
    0.68
     Descriptors
    0.66
     Frames
    0.65
    expandindo
    0.64
    rovnik
    0.64
     configureStore
    0.63
    цездатний
    0.63
    Activations Density 1.139%

    No Known Activations