© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10333
    Prev
    Next
    INDEX
    Explanations

    words related to roofing materials and manufacturing

    oai_token-act-pair · gemini-2.0-flash

    Technical/formal documents

    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
    AndEndTag
    -0.78
    rrggbb
    -0.63
    FormBuilder
    -0.62
    ContentAsync
    -0.61
    DoubleQuotes
    -0.59
    setopt
    -0.56
    LookAnd
    -0.52
    uspiel
    -0.52
     Photocase
    -0.51
     jsPsych
    -0.49
    POSITIVE LOGITS
    mien
    0.54
     scolaires
    0.51
    :+:
    0.49
     fédé
    0.48
     appelez
    0.47
     Petersen
    0.46
     bascul
    0.46
    Revenir
    0.45
     Master
    0.45
     religieuses
    0.44
    Activations Density 1.383%

    No Known Activations