Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12111
    Prev
    Next
    INDEX
    Explanations

    the start of the word "Constitution" or "Consolidated"

    oai_token-act-pair · gemini-2.0-flash

    Cons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    protoimpl
    -0.50
    ském
    -0.49
    Semif
    -0.48
    omitempty
    -0.47
     remote
    -0.47
     D
    -0.47
     rest
    -0.47
    urlpatterns
    -0.46
     Black
    -0.45
     black
    -0.45
    POSITIVE LOGITS
     ostavi
    0.84
     >=",
    0.69
    horabuena
    0.66
     مشارکت‌کنندگان
    0.66
    piram
    0.65
    Билгалдахарш
    0.65
    numerusform
    0.64
     fubject
    0.64
    providedIn
    0.63
     jäsen
    0.63
    Activations Density 1.517%

    No Known Activations