© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14400
    Prev
    Next
    INDEX
    Explanations

    code related to testing and debugging JavaScript code

    oai_token-act-pair · gemini-2.0-flash

    Numbers three and four

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Efq
    -1.09
     ModelExpression
    -1.07
     AssemblyProduct
    -1.07
     raiſ
    -0.98
     becauſe
    -0.95
     wireType
    -0.94
    titleMargin
    -0.94
     perfons
    -0.93
     theſe
    -0.93
     autorytatywna
    -0.93
    POSITIVE LOGITS
    3
    0.63
    4
    0.57
    三
    0.52
     kla
    0.44
    ur
    0.41
    0.41
    서
    0.41
    四
    0.40
            
    0.39
     three
    0.39
    Activations Density 1.868%
    No Known Activations