© 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. 13833
    Prev
    Next
    INDEX
    Explanations

    parts of programming code or file paths

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    AutoScale
    -0.50
     indisponible
    -0.49
     '&#
    -0.47
    渉
    -0.45
    apat
    -0.44
     Empieza
    -0.44
    makeText
    -0.44
    
    -0.44
    олові
    -0.43
     lesson
    -0.43
    POSITIVE LOGITS
    alleros
    0.66
    SharedDtor
    0.64
    verifyException
    0.64
    ISupport
    0.63
    MessageOf
    0.59
    URLException
    0.59
     présidenti
    0.59
     jspb
    0.58
    unknownFields
    0.58
    jspb
    0.58
    Activations Density 0.409%

    No Known Activations