© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6818
    Prev
    Next
    INDEX
    Explanations

    legal documents and proceedings

    oai_token-act-pair · gemini-2.0-flash

    hearing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     was
    -0.68
     in
    -0.68
     for
    -0.60
    yntaxException
    -0.59
     care
    -0.59
     and
    -0.57
     made
    -0.57
     with
    -0.56
    annah
    -0.56
    ịch
    -0.56
    POSITIVE LOGITS
    <bos>
    0.99
    BeginInit
    0.90
    Tembelea
    0.88
     disambiguazione
    0.85
    rungsseite
    0.85
    
    0.83
     utafitiHapana
    0.79
     незавершена
    0.77
     Administrativna
    0.75
     nakalista
    0.73
    Activations Density 1.080%

    No Known Activations