© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13821
    Prev
    Next
    INDEX
    Explanations

    content related to business and advertising

    oai_token-act-pair · gemini-2.0-flash

    per

    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
     AppCompatTheme
    -0.62
    dymyr
    -0.60
     MotionEvent
    -0.58
    cagon
    -0.56
    byshev
    -0.55
    InjectAttribute
    -0.54
    NOPQRST
    -0.53
    ็ง
    -0.53
     AsyncTask
    -0.52
    nhà
    -0.51
    POSITIVE LOGITS
     per
    2.59
    per
    1.91
    Per
    1.83
     Per
    1.82
     PER
    1.61
    PER
    1.45
     perse
    0.88
    每
    0.88
     unit
    0.84
    PerPage
    0.83
    Activations Density 2.257%

    No Known Activations