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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14712
    Prev
    Next
    INDEX
    Explanations

    the prefix "bi" or the string "Fi"

    oai_token-act-pair · gemini-2.0-flash

    Bilayers, science

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ა
    -0.56
    الإنجليزية
    -0.53
    ce
    -0.52
    es
    -0.51
    li
    -0.50
    ய
    -0.49
    ve
    -0.48
    ga
    -0.47
    f
    -0.46
    ci
    -0.45
    POSITIVE LOGITS
    IBOutlet
    0.62
    存于互联网档案馆
    0.60
    ContentAlignment
    0.58
    yel
    0.56
    exactly
    0.55
    AnchorStyles
    0.54
    yka
    0.53
    dotte
    0.53
     IBOutlet
    0.52
    enough
    0.52
    Activations Density 1.466%

    No Known Activations