© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11880
    Prev
    Next
    INDEX
    Explanations

    instances of people asking "how to" do something

    oai_token-act-pair · gemini-2.0-flash

    "How to" questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    \}\\
    -0.51
    ForValue
    -0.46
    RenderAtEndOf
    -0.46
    expandindo
    -0.45
    withId
    -0.45
    letics
    -0.45
     незавершена
    -0.44
     at
    -0.43
    DeleteBehavior
    -0.43
    済み
    -0.43
    POSITIVE LOGITS
    CppCodeGen
    0.64
    scriptcase
    0.52
     препратки
    0.52
     localObject
    0.50
    webElementXpaths
    0.50
    ReadLine
    0.50
     Cite
    0.50
    kozá
    0.50
    sonaro
    0.50
    WriteBarrier
    0.49
    Activations Density 6.195%

    No Known Activations