© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14192
    Prev
    Next
    INDEX
    Explanations

    code with square brackets

    oai_token-act-pair · gemini-2.0-flash

    opening bracket

    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
    Method
    -0.51
    DbContext
    -0.50
    totalPages
    -0.48
    reszcie
    -0.47
    deltaTime
    -0.45
     ayrı
    -0.45
     Method
    -0.45
    фессиона
    -0.45
     entanto
    -0.44
    ranton
    -0.43
    POSITIVE LOGITS
     nahilalakip
    0.95
    tagHelperRunner
    0.79
     betweenstory
    0.77
    oredCriteria
    0.76
    RegistryLite
    0.69
     kaarangay
    0.68
    AndEndTag
    0.67
    withIdentifier
    0.67
    Попис
    0.65
    RTEX
    0.63
    Activations Density 0.581%

    No Known Activations