© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4180
    Prev
    Next
    INDEX
    Explanations

    legal quotations and bracketed insertions in legal text, also flagging general discussion of political situations

    oai_token-act-pair · gemini-2.0-flash

    opening square bracket

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    FormTagHelper
    -0.76
     intStringLen
    -0.56
     Es
    -0.52
    modelBuilder
    -0.51
    ">//
    -0.48
    معلومات
    -0.48
    IsMutable
    -0.48
    irited
    -0.47
     keamanan
    -0.47
    onsored
    -0.46
    POSITIVE LOGITS
     Seligman
    0.62
    
    0.60
    tvguidetime
    0.57
    stateProvider
    0.57
    BASEPATH
    0.56
    PreferredItem
    0.56
     BIBSYS
    0.53
     NIOS
    0.53
    ResponseEntity
    0.52
    െയ
    0.52
    Activations Density 1.581%

    No Known Activations