© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6797
    Prev
    Next
    INDEX
    Explanations

    several abstract relationships between words without a clear unifying theme

    oai_token-act-pair · gemini-2.0-flash

    very/extremely

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Normdatei
    -1.13
    Geplaatst
    -1.04
    sizeCache
    -1.01
    تقاوى
    -0.97
    IsMutable
    -0.96
     kaarangay
    -0.95
     Efq
    -0.95
     Monfieur
    -0.94
     ſeveral
    -0.93
     myſelf
    -0.93
    POSITIVE LOGITS
     very
    1.11
     extremely
    0.94
    very
    0.85
     VERY
    0.85
     Very
    0.80
    Very
    0.79
     incredibly
    0.79
    extremely
    0.75
     muy
    0.72
     très
    0.69
    Activations Density 1.031%

    No Known Activations