© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10175
    Prev
    Next
    INDEX
    Explanations

    angle brackets, dollar signs, number signs, periods, semicolons, and commas that appear in code

    oai_token-act-pair · gemini-2.0-flash

    Code/math snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ...
    -0.73
    …
    -0.70
    ,
    -0.68
     
    -0.66
     (
    -0.65
    -
    -0.65
    ↵
    -0.65
    1
    -0.64
    "
    -0.64
      
    -0.63
    POSITIVE LOGITS
     Efq
    1.26
     Theſe
    1.13
     Савезне
    1.12
     myſelf
    1.09
     Monfieur
    1.09
     itſelf
    1.05
     raiſ
    1.05
     Anſ
    1.00
     houſe
    0.96
     purpoſe
    0.96
    Activations Density 5.078%

    No Known Activations