© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1421
    Prev
    Next
    INDEX
    Explanations

    java code

    oai_token-act-pair · gemini-2.0-flash

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    -0.68
     فريبيس
    -0.63
    MigrationBuilder
    -0.60
    CloseOperation
    -0.59
    ="@+
    -0.57
    posedge
    -0.57
     MainAxisSize
    -0.55
    didSet
    -0.54
    stdc
    -0.54
    SourceChecksum
    -0.54
    POSITIVE LOGITS
     kasarigan
    0.67
    opha
    0.55
     Roskov
    0.51
    hogy
    0.51
    <bos>
    0.50
     tranquility
    0.50
     testy
    0.49
     EconPapers
    0.49
     Aton
    0.49
    omock
    0.48
    Activations Density 0.955%

    No Known Activations