© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6617
    Prev
    Next
    INDEX
    Explanations

    spaces between words and punctuation in a legal document

    oai_token-act-pair · gemini-2.0-flash

    repetitive text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Geplaatst
    -0.83
     незавершена
    -0.68
    ViewFeatures
    -0.68
    OGND
    -0.68
    enterOuterAlt
    -0.66
     препратки
    -0.64
    kháu
    -0.63
    ngdoc
    -0.62
     InputDecoration
    -0.57
    StoreMessageInfo
    -0.56
    POSITIVE LOGITS
     invokingState
    0.59
     Normdatei
    0.52
    kfree
    0.51
    ngOn
    0.51
     laiton
    0.51
     préf
    0.50
     variés
    0.49
     Stor
    0.49
     يلي
    0.49
     partea
    0.48
    Activations Density 1.600%

    No Known Activations