© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12236
    Prev
    Next
    INDEX
    Explanations

    exam/quiz scoring and permission/access matrixes

    oai_token-act-pair · gemini-2.0-flash

    exam

    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
    pyplot
    -0.54
    gonic
    -0.51
     correctes
    -0.48
    titleMargin
    -0.48
    featureID
    -0.48
    uxxxx
    -0.47
    IBinder
    -0.47
    
    -0.47
     استنادى
    -0.46
     pars
    -0.45
    POSITIVE LOGITS
     <=",
    0.81
    ConstraintMaker
    0.62
     متعلقه
    0.61
    SequentialGroup
    0.60
     Normdatei
    0.55
     fieldNum
    0.55
    XmlEnum
    0.54
     INTERESAR
    0.52
    icular
    0.50
    AccessException
    0.50
    Activations Density 0.666%

    No Known Activations