© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14959
    Prev
    Next
    INDEX
    Explanations

    code snippets that use "self" within classes and related keywords

    oai_token-act-pair · gemini-2.0-flash

    self

    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>
    -0.99
    '
    -0.60
     culoare
    -0.56
     profondo
    -0.54
    al
    -0.50
     viata
    -0.50
     alın
    -0.50
     piú
    -0.49
     spéciales
    -0.49
    ↵↵
    -0.48
    POSITIVE LOGITS
    ValueStyle
    1.19
    parsedMessage
    1.15
     kasarigan
    1.12
    oredCriteria
    1.09
    awtextra
    1.08
    BeginInit
    1.08
    GEBURTSDATUM
    1.08
     "..\..\
    1.07
     <<<<<<<<<<<<<<
    1.06
    TypedDataSet
    1.01
    Activations Density 1.896%

    No Known Activations