© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11675
    Prev
    Next
    INDEX
    Explanations

    large blocks of whitespace in the document

    oai_token-act-pair · gemini-2.0-flash

    code or technical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     وتسجيلات
    -0.63
     الرياضيه
    -0.59
    findpost
    -0.54
     دیکھیے
    -0.51
    RegressionTest
    -0.50
     IFTT
    -0.50
    المناصب
    -0.49
    الدراسه
    -0.48
    Vidite
    -0.46
    Chham
    -0.45
    POSITIVE LOGITS
    addGap
    0.60
    AccessorTable
    0.51
    migrationBuilder
    0.47
    новништво
    0.47
    mockMvc
    0.46
    PROLOG
    0.45
     onData
    0.45
    ліст
    0.42
    ;#
    0.42
    <bos>
    0.41
    Activations Density 3.064%

    No Known Activations