© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9202
    Prev
    Next
    INDEX
    Explanations

    LaTeX array environments

    oai_token-act-pair · gemini-2.0-flash

    Array

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     UIKit
    -0.64
     Schre
    -0.61
    ########.
    -0.60
    SharedDtor
    -0.58
    ++){
    -0.58
    InputTagHelper
    -0.58
    estinations
    -0.57
    redients
    -0.57
    richTextPanel
    -0.57
    abstractmethod
    -0.55
    POSITIVE LOGITS
     ſche
    0.59
    ScopeManager
    0.56
     houſe
    0.55
     كومونز
    0.53
     purpoſe
    0.49
     reaſon
    0.48
     ſta
    0.48
     OMITBAD
    0.48
     poffe
    0.48
    UnknownFields
    0.47
    Activations Density 1.534%

    No Known Activations