© 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. 10166
    Prev
    Next
    INDEX
    Explanations

    snippets of text about networking or connections between devices or systems

    oai_token-act-pair · gemini-2.0-flash

    connection

    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
    攘
    -0.54
    ÍAS
    -0.52
     Shand
    -0.49
    ries
    -0.46
     élo
    -0.46
    kadi
    -0.46
     onSave
    -0.46
    allus
    -0.45
     Aj
    -0.45
    ker
    -0.45
    POSITIVE LOGITS
    ReusableCell
    0.79
     to
    0.75
    migrationBuilder
    0.68
    StoryboardSegue
    0.65
    AndEndTag
    0.61
     SwitchCompat
    0.61
     مشين
    0.61
     propOrder
    0.61
     AssemblyCulture
    0.61
    原始内容存档于
    0.61
    Activations Density 5.180%

    No Known Activations