© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2460
    Prev
    Next
    INDEX
    Explanations

    a mix of URLs, shopping-related words, and also past tense verbs related to buying

    oai_token-act-pair · gemini-2.0-flash

    links, purchases, gifts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    deinit
    -0.55
     mapStateToProps
    -0.52
    osoma
    -0.48
     {?
    -0.48
     iunie
    -0.45
    тиво
    -0.44
    ukses
    -0.44
    δο
    -0.43
     ORIENT
    -0.43
     môžu
    -0.42
    POSITIVE LOGITS
    Xna
    0.74
    脚注の使い方
    0.74
    ImageContext
    0.71
    MessageTagHelper
    0.69
    íncia
    0.69
    IUrlHelper
    0.68
    DebuggerStep
    0.66
     Référence
    0.65
     bpy
    0.65
    Portale
    0.63
    Activations Density 0.874%

    No Known Activations