© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10481
    Prev
    Next
    INDEX
    Explanations

    words related to construction, plumbing or infrastructure maintenance

    oai_token-act-pair · gemini-2.0-flash

    drainage or registration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     quadrant
    -0.60
     Majefty
    -0.57
    ViewFeatures
    -0.56
     Lire
    -0.55
    tagHelper
    -0.55
    icity
    -0.55
     increments
    -0.54
     CreateTagHelper
    -0.54
    teren
    -0.52
    Bism
    -0.52
    POSITIVE LOGITS
     nonUne
    0.66
     فريبيس
    0.66
    WebpackPlugin
    0.64
     محفوظة
    0.61
     незавершена
    0.60
    SourceChecksum
    0.58
    UserScript
    0.55
     estimés
    0.53
    ChildScrollView
    0.52
     ويكيميديا
    0.52
    Activations Density 7.745%

    No Known Activations