© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12355
    Prev
    Next
    INDEX
    Explanations

    places where something is described as "so" (something)

    oai_token-act-pair · gemini-2.0-flash

    say "much/many"

    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
     lots
    -1.67
     lot
    -1.55
     Lots
    -1.47
    Lots
    -1.45
    lots
    -1.43
     LOTS
    -1.27
     alot
    -1.22
    Lot
    -1.17
     LOT
    -1.16
     Lot
    -1.13
    POSITIVE LOGITS
     much
    0.93
    much
    0.84
     Much
    0.80
    Much
    0.77
     MUCH
    0.65
     mush
    0.61
    Jeografia
    0.56
    ulaires
    0.52
     Zus
    0.52
    Instrucciones
    0.51
    Activations Density 1.308%

    No Known Activations