© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2005
    Prev
    Next
    INDEX
    Explanations

    text discussing confidence intervals, standard deviations, variance, and other statistical measures

    oai_token-act-pair · gemini-2.0-flash

    statistical data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    openConnection
    -0.63
    WebElementEntity
    -0.61
    WithIOException
    -0.58
     ProtoMessage
    -0.57
     consultato
    -0.57
    XmlAccessorType
    -0.55
    pegno
    -0.54
     AssemblyCompany
    -0.54
    ToListAsync
    -0.53
    complexContent
    -0.53
    POSITIVE LOGITS
    fører
    0.56
     centrales
    0.56
     оригіналу
    0.56
    StoreMessageInfo
    0.52
    før
    0.52
     quantify
    0.50
     فريبيس
    0.49
     wikipagina
    0.49
     تانيه
    0.46
    AccessorTable
    0.46
    Activations Density 17.463%

    No Known Activations