© 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. 14566
    Prev
    Next
    INDEX
    Explanations

    mentions of scientific development and breakthrough

    oai_token-act-pair · gemini-2.0-flash

    innovation

    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
    tagHelperRunner
    -0.79
     <>",
    -0.75
    CreateModel
    -0.64
    oredCriteria
    -0.64
    yntaxException
    -0.64
    sizeCache
    -0.63
    InitVars
    -0.61
    fillType
    -0.61
     createState
    -0.60
    principalColumn
    -0.58
    POSITIVE LOGITS
     depositphotos
    0.60
     fubject
    0.59
    ances
    0.57
    itados
    0.56
    מבר
    0.56
    ASSOCI
    0.56
     poffible
    0.55
    tably
    0.53
     paff
    0.53
     perfons
    0.53
    Activations Density 0.752%

    No Known Activations