© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16330
    Prev
    Next
    INDEX
    Explanations

    references to fundamental or critical concepts

    oai_token-act-pair · gemini-2.0-flash

    key

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     critical
    -1.08
    critical
    -1.05
     Critical
    -1.01
    Critical
    -0.98
     estekak
    -0.93
     nahilalakip
    -0.88
    IUrlHelper
    -0.86
    GOTREF
    -0.85
     critically
    -0.84
     CRITICAL
    -0.84
    POSITIVE LOGITS
     en
    0.61
     take
    0.52
    take
    0.52
     to
    0.50
    en
    0.48
    uh
    0.45
    les
    0.43
    ban
    0.43
     dej
    0.43
     takes
    0.43
    Activations Density 3.879%

    No Known Activations