© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6558
    Prev
    Next
    INDEX
    Explanations

    source code and markup language snippets

    oai_token-act-pair · gemini-2.0-flash

    Code or data assignment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.02
    ChildScrollView
    -0.84
    setVerticalGroup
    -0.81
     <>",
    -0.79
     getItemId
    -0.78
     '\\;'
    -0.78
    NamedQueries
    -0.71
    LLocation
    -0.67
    NewUrlParser
    -0.66
    ConstraintMaker
    -0.66
    POSITIVE LOGITS
    RenderAtEndOf
    0.54
     ())
    0.47
     meanwhile
    0.47
    Références
    0.46
    apache
    0.45
     "[
    0.44
     dita
    0.44
     Watson
    0.44
     tess
    0.44
    zioni
    0.43
    Activations Density 4.801%

    No Known Activations