© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13809
    Prev
    Next
    INDEX
    Explanations

    code snippets with certain formatting and keywords such as "BEGIN", "END", "Python" and "error"

    oai_token-act-pair · gemini-2.0-flash

    Separator Tokens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     intptr
    -0.72
    IndentedString
    -0.68
    msgTypes
    -0.66
    paksa
    -0.63
    migrationBuilder
    -0.63
     InputDecoration
    -0.60
    removeChild
    -0.59
     ImportError
    -0.59
    tisseur
    -0.58
     Abhishek
    -0.58
    POSITIVE LOGITS
    <bos>
    0.67
    BagConstraints
    0.54
     незавершена
    0.50
     pratica
    0.50
     كومونز
    0.50
    CreateModel
    0.49
    archiviato
    0.48
     للاسماء
    0.48
     beginnetje
    0.47
     şöyle
    0.46
    Activations Density 2.841%

    No Known Activations