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. 14875
    Prev
    Next
    INDEX
    Explanations

    instances of reporting information from news articles or other formal investigations

    oai_token-act-pair · gemini-2.0-flash

    article snippets

    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
     Мексичка
    -0.58
    ByExample
    -0.57
    principalColumn
    -0.57
    rawDesc
    -0.55
     кӀ
    -0.55
    betical
    -0.53
    basicConfig
    -0.53
     FetchType
    -0.52
    copg
    -0.52
    DockStyle
    -0.51
    POSITIVE LOGITS
     our
    1.05
     their
    0.96
     its
    0.84
    $'
    0.68
    their
    0.67
    our
    0.64
     his
    0.63
     deras
    0.60
     the
    0.59
     dessen
    0.58
    Activations Density 2.614%

    No Known Activations