© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15434
    Prev
    Next
    INDEX
    Explanations

    the mention of the sports team Manchester United

    oai_token-act-pair · gemini-2.0-flash

    UK cities and football

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ³)
    -0.45
    amos
    -0.44
    缩
    -0.42
    rollers
    -0.42
    arith
    -0.42
    UMMY
    -0.42
     Moisés
    -0.42
     Gleich
    -0.40
    リム
    -0.40
     Gregor
    -0.40
    POSITIVE LOGITS
    AddTagHelper
    0.91
    tagHelperRunner
    0.79
     تانيه
    0.73
    LEncoder
    0.64
     оригіналу
    0.64
    webElementGuid
    0.63
     Савезне
    0.63
    +#+#
    0.61
    TypedDataSet
    0.60
     médicaux
    0.60
    Activations Density 0.141%

    No Known Activations