© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6501
    Prev
    Next
    INDEX
    Explanations

    HTML markup tags, especially related to lists and descriptions

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ConstraintMaker
    -0.66
     CreateTagHelper
    -0.54
    Personendaten
    -0.53
     lèvres
    -0.51
    AccessorTable
    -0.51
     mukaan
    -0.51
    HasKey
    -0.50
    verture
    -0.50
     souple
    -0.50
     soto
    -0.50
    POSITIVE LOGITS
    tanleria
    0.62
    istoitu
    0.60
    ArgsConstructor
    0.57
     viewDidLoad
    0.53
    //
    0.53
     SafeMath
    0.52
    [][]
    0.52
     yii
    0.49
     يتيمه
    0.48
    perror
    0.46
    Activations Density 0.025%

    No Known Activations