© 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. 11932
    Prev
    Next
    INDEX
    Explanations

    abstract concepts, such as scenarios, states, and points of progress

    oai_token-act-pair · gemini-2.0-flash

    where

    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
     in
    -0.79
     with
    -0.55
    dalam
    -0.50
    findpost
    -0.50
    Примечания
    -0.47
     for
    -0.45
     dalam
    -0.44
    曖昧さ回避
    -0.44
     в
    -0.43
     With
    -0.43
    POSITIVE LOGITS
     where
    1.84
    where
    1.55
     où
    1.36
     donde
    1.32
    Where
    1.27
     Where
    1.23
     где
    1.23
     wher
    1.23
     WHERE
    1.15
     όπου
    1.15
    Activations Density 0.180%

    No Known Activations