© 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. 13785
    Prev
    Next
    INDEX
    Explanations

    code blocks with indentation

    oai_token-act-pair · gemini-2.0-flash

    Code/foreign words

    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
     Gla
    -0.57
    ContentAsync
    -0.56
    ])))
    -0.56
     sixth
    -0.55
    geth
    -0.53
     Mini
    -0.52
     eighth
    -0.52
     Saturday
    -0.51
     بيها
    -0.51
     Satur
    -0.50
    POSITIVE LOGITS
    StoryboardSegue
    0.68
    tvguidetime
    0.58
     écoute
    0.56
    ponses
    0.55
     Betracht
    0.55
    riwal
    0.52
     namanya
    0.51
     JpaRepository
    0.49
    ukų
    0.49
    ❸
    0.49
    Activations Density 0.284%

    No Known Activations